R Under development (unstable) (2026-07-21 r90286) -- "Unsuffered Consequences" Copyright (C) 2026 The R Foundation for Statistical Computing Platform: x86_64-pc-linux-gnu R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. Natural language support but running in an English locale R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. > pkgname <- "clustGLMM" > source(file.path(R.home("share"), "R", "examples-header.R")) > options(warn = 1) > library('clustGLMM') > > base::assign(".oldSearch", base::search(), pos = 'CheckExEnv') > base::assign(".old_wd", base::getwd(), pos = 'CheckExEnv') > cleanEx() > nameEx("as_coda") > ### * as_coda > > flush(stderr()); flush(stdout()) > > ### Name: as_coda > ### Title: Change the Output Formats of 'clustGLMM' > ### Aliases: as_coda from_C_to_list from_C_to_matrix from_list_to_C > ### from_list_to_coda from_list_to_matrix from_matrix_to_C > ### from_matrix_to_coda from_matrix_to_list > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) newton_raphson.c:287:34: runtime error: negation of -2147483648 cannot be represented in type 'int'; cast to an unsigned type to negate this value to itself #0 0x7b3686064c36 in newton_raphson /data/localhost/ripley/R/packages/tests-gcc-SAN/clustGLMM/src/newton_raphson.c:287 #1 0x7b36860739c9 in metrgibbs_beta_ord /data/localhost/ripley/R/packages/tests-gcc-SAN/clustGLMM/src/metrgibbs_beta_ord.c:122 #2 0x7b368602eedf in Metropolis_within_Gibbs_MBC_NumPoiBinOrdCat /data/localhost/ripley/R/packages/tests-gcc-SAN/clustGLMM/src/Metropolis_within_Gibbs_MBC_NumPoiBinOrdCat.c:1490 #3 0x000000775f4c in do_dotCode /data/localhost/ripley/R/svn/R-devel/src/main/dotcode.c:2488 #4 0x0000008eb97b in bcEval_loop /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:8150 #5 0x0000008d687b in bcEval /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:7533 #6 0x000000877eba in Rf_eval /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:1167 #7 0x00000088e6ca in R_execClosure /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:2398 #8 0x00000089235d in applyClosure_core /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:2314 #9 0x000000878568 in Rf_applyClosure /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:2333 #10 0x000000878568 in Rf_eval /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:1278 #11 0x0000008a689e in do_set /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:3585 #12 0x000000878996 in Rf_eval /data/localhost/ripley/R/svn/R-devel/src/main/eval.c:1230 #13 0x000000a1ee48 in Rf_ReplIteration /data/localhost/ripley/R/svn/R-devel/src/main/main.c:264 #14 0x000000a1ee48 in R_ReplConsole /data/localhost/ripley/R/svn/R-devel/src/main/main.c:317 #15 0x000000a3cada in run_Rmainloop /data/localhost/ripley/R/svn/R-devel/src/main/main.c:1237 #16 0x000000a3cb72 in Rf_mainloop /data/localhost/ripley/R/svn/R-devel/src/main/main.c:1244 #17 0x000000411f5f in main /data/localhost/ripley/R/svn/R-devel/src/main/Rmain.c:29 #18 0x7f3692a0a680 in __libc_start_call_main (/lib64/libc.so.6+0x3680) (BuildId: 17f2e1fd905f485786f6fd6e3bede4ad737137e7) #19 0x7f3692a0a797 in __libc_start_main@GLIBC_2.2.5 (/lib64/libc.so.6+0x3797) (BuildId: 17f2e1fd905f485786f6fd6e3bede4ad737137e7) #20 0x000000412924 in _start (/data/localhost/ripley/R/gcc-SAN3/bin/exec/R+0x412924) (BuildId: 7bd069e7b1c3f2758f94ae347cb95ae3bb7314b6) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### Changing formats > ###----------------------------------------------------------------------------- > > ## How to change from "data.frame"="matrix" to "list": > mcmc <- from_matrix_to_list(mcmc) > > ## How to change from "list" to "data.frame"="matrix": > mcmc <- from_list_to_matrix(mcmc) > > ## How to change from "data.frame"="matrix" to mcmc from 'coda' package > codamcmc <- from_matrix_to_coda(mcmc, burnin = 10, thin = 1) > > ## How to change from any howsave type to mcmc from 'coda' package > codamcmc <- as_coda(mcmc, burnin = 10, thin = 1) > > > > cleanEx() > nameEx("clustGLMM") > ### * clustGLMM > > flush(stderr()); flush(stdout()) > > ### Name: clustGLMM > ### Title: Sample MCMC for a Mixture of GLMMs of Mixed-type > ### Aliases: clustGLMM > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ## Extract the last state > inits <- mcmc$last > > ## Initialize with inits = Continue in sampling from the last state > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + inits = inits, + G = Gmax, iter = 100, nchains = nchains) Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ## Note that sampling takes time, here we generate too short chains. > ## Sample longer chains for more faithful posterior approximation. > ## Parallelization for different chains is recommended. > ## See the vignette for more examples. > > > > cleanEx() > nameEx("clustering_probabilities_and_deviance") > ### * clustering_probabilities_and_deviance > > flush(stderr()); flush(stdout()) > > ### Name: clustering_probabilities_and_deviance > ### Title: Evaluate Clustering Probabilities and Deviance of Output of > ### 'clustGLMM' > ### Aliases: clustering_probabilities_and_deviance > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 1 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. All chains have been sampled. > > ## Extract the last state > inits <- mcmc$last > > ## Initialize with inits = Continue in sampling from the last state > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + inits = inits, + G = Gmax, iter = 100, nchains = nchains) Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. All chains have been sampled. > > ## Note that sampling takes time, here we generate too short chains. > ## Sample longer chains for more faithful posterior approximation. > ## Parallelization for different chains is recommended. > ## See the vignette for more examples. > > ###----------------------------------------------------------------------------- > ### Sample completely new data > ###----------------------------------------------------------------------------- > nnew <- 100 > n_i <- 4 > G <- 2 > timepar <- "mix" > catpar <- "no" > catsubjfix <- TRUE > xin1 <- 1 > Kord <- 5 > Kcat <- 4 > kspec_bi_cat <- FALSE > corr <- matrix(c(1, -0.5, -0.5, -0.4, -0.4, + -0.5, 1, 0.3, 0.4, 0.5, + -0.5, 0.3, 1, 0.2, 0.3, + -0.4, 0.4, 0.2, 1, 0.1, + -0.4, 0.5, 0.3, 0.1, 1), byrow = TRUE, ncol = 5) > sdSigmas <- c(0.5, 0.5, 0.5, 0.5, 0.5) > Sigma <- diag(sdSigmas) > > set.seed(27818) > ldatanew <- generate_longitudinal_mixed_type_data(n = nnew, n_i = 4, + G = 2, timepar = "cross", catpar = "fixed", + catsubjfix = TRUE, + xin1 = 1, Sigma = Sigma, + Kord = 5, Kcat = 4, kspec_bi_cat = FALSE) > newdata <- ldatanew$data > > ###----------------------------------------------------------------------------- > ### Evaluate the clustering probabilities for newdata > ###----------------------------------------------------------------------------- > > probs <- clustering_probabilities_and_deviance(mcmc, id, newdata, + dynamic_prob = FALSE, + start = 1, + end = 100, + thin = 2, + chains = 1:nchains, + tolerance = 1e-7, + maxiter = 100, + maxnrep = 20, + NGQ = 1) Chain: 1, (2 %) Chain: 1, (4 %) Chain: 1, (6 %) Chain: 1, (8 %) Chain: 1, (10 %) Chain: 1, (12 %) Chain: 1, (14 %) Chain: 1, (16 %) Chain: 1, (18 %) Chain: 1, (20 %) Chain: 1, (22 %) Chain: 1, (24 %) Chain: 1, (26 %) Chain: 1, (28 %) Chain: 1, (30 %) Chain: 1, (32 %) Chain: 1, (34 %) Chain: 1, (36 %) Chain: 1, (38 %) Chain: 1, (40 %) Chain: 1, (42 %) Chain: 1, (44 %) Chain: 1, (46 %) Chain: 1, (48 %) Chain: 1, (50 %) Chain: 1, (52 %) Chain: 1, (54 %) Chain: 1, (56 %) Chain: 1, (58 %) Chain: 1, (60 %) Chain: 1, (62 %) Chain: 1, (64 %) Chain: 1, (66 %) Chain: 1, (68 %) Chain: 1, (70 %) Chain: 1, (72 %) Chain: 1, (74 %) Chain: 1, (76 %) Chain: 1, (78 %) Chain: 1, (80 %) Chain: 1, (82 %) Chain: 1, (84 %) Chain: 1, (86 %) Chain: 1, (88 %) Chain: 1, (90 %) Chain: 1, (92 %) Chain: 1, (94 %) Chain: 1, (96 %) Chain: 1, (98 %) Chain: 1, (100 %) > > ###----------------------------------------------------------------------------- > ### Final clustering > ###----------------------------------------------------------------------------- > certainty <- probs$certainty > clustering <- probs$clustering > # To be classified in the cluster with maximal clustering probability, > # it has to overcome the given threshold, otherwise remains unclassified. > threshold <- 0.8 > clustering[certainty < threshold] <- 0 > > ch <- 1 > newdata$clustering <- clustering[,ch] > > newdata1 <- newdata[newdata$j==1,] > table(newdata1$clustering, newdata1$g) 1 2 0 12 16 1 15 13 3 19 25 > # row 0: unclassified > > > > > cleanEx() > nameEx("default_varying") > ### * default_varying > > flush(stderr()); flush(stdout()) > > ### Name: default_varying > ### Title: Setting Default Values in 'clustGLMM' > ### Aliases: default_param default_save default_tuning default_varying > > ### ** Examples > > (param <- default_param()) $InvSigma_df [1] 1 $InvQ_df [1] 1 $prec_num_shp [1] 1 $prec_num_rte [1] 10 $beta_num_fix_sd [1] 1 $beta_num_sd [1] 1 $beta_poi_fix_sd [1] 1 $beta_poi_sd [1] 1 $beta_bin_fix_sd [1] 1 $beta_bin_sd [1] 1 $beta_ord_fix_sd [1] 1 $beta_ord_sd [1] 1 $api_prior [1] 1 $beta_cat_fix_sd [1] 1 $beta_cat_sd [1] 1 $init_b_sd [1] 0.01 $e0_shp [1] 1 $e0_rte [1] 100 $InvV [1] 0.01 > (param <- default_param(sparse = FALSE)) $InvSigma_df [1] 1 $InvQ_df [1] 1 $prec_num_shp [1] 1 $prec_num_rte [1] 10 $beta_num_fix_sd [1] 1 $beta_num_sd [1] 1 $beta_poi_fix_sd [1] 1 $beta_poi_sd [1] 1 $beta_bin_fix_sd [1] 1 $beta_bin_sd [1] 1 $beta_ord_fix_sd [1] 1 $beta_ord_sd [1] 1 $api_prior [1] 1 $beta_cat_fix_sd [1] 1 $beta_cat_sd [1] 1 $init_b_sd [1] 0.01 $e0_shp [1] 4 $e0_rte [1] 1 $InvV [1] 0.01 > (save <- default_save()) beta_num_fix beta_num prec_num sd_num var_num beta_poi_fix TRUE TRUE TRUE TRUE TRUE TRUE beta_poi beta_bin_fix beta_bin beta_ord_fix beta_ord c_ord TRUE TRUE TRUE TRUE TRUE TRUE a_ord pi_ord beta_cat_fix beta_cat InvSigma Sigma FALSE TRUE TRUE TRUE TRUE TRUE sdSigma corSigma detInvSigma InvQ Q detInvQ TRUE TRUE FALSE FALSE FALSE FALSE b w ng loglik pUig U FALSE TRUE TRUE TRUE FALSE TRUE Gplus e0 naY TRUE TRUE FALSE > (tuning <- default_tuning()) $integer $integer$freq_proposal_update [1] 10 $integer$times_proposal [1] 1 $integer$maxiter [1] 25 $integer$maxnrep [1] 100 $integer$kspec_bi_cat [1] 0 $double $double$const_proposal_beta_poi_fix [1] 1 $double$const_proposal_beta_poi [1] 1 $double$const_proposal_beta_bin_fix [1] 1 $double$const_proposal_beta_bin [1] 1 $double$const_proposal_beta_ord_fix [1] 1 $double$const_proposal_beta_ord [1] 1 $double$const_proposal_beta_cat_fix [1] 1 $double$const_proposal_beta_cat [1] 1 $double$const_proposal_a_ord [1] 1 $double$const_proposal_b [1] 1 $double$const_proposal_e0 [1] 1 $double$tolerance [1] 1e-07 > (tuning <- default_tuning(experience = TRUE)) $integer $integer$freq_proposal_update [1] 10 $integer$times_proposal [1] 10 $integer$maxiter [1] 25 $integer$maxnrep [1] 100 $integer$kspec_bi_cat [1] 0 $double $double$const_proposal_beta_poi_fix [1] 1 $double$const_proposal_beta_poi [1] 1 $double$const_proposal_beta_bin_fix [1] 1 $double$const_proposal_beta_bin [1] 1 $double$const_proposal_beta_ord_fix [1] 0.5 $double$const_proposal_beta_ord [1] 0.5 $double$const_proposal_beta_cat_fix [1] 1 $double$const_proposal_beta_cat [1] 1 $double$const_proposal_a_ord [1] 0.5 $double$const_proposal_b [1] 0.5 $double$const_proposal_e0 [1] 1 $double$tolerance [1] 1e-07 > (varying <- default_varying()) prec_num c_ord InvSigma InvQ naY TRUE TRUE FALSE FALSE FALSE > > > > > cleanEx() > nameEx("generate_longitudinal_mixed_type_data") > ### * generate_longitudinal_mixed_type_data > > flush(stderr()); flush(stdout()) > > ### Name: generate_longitudinal_mixed_type_data > ### Title: Generate an Artificial Longitudinal Dataset with Mixed-type > ### Outcomes > ### Aliases: generate_longitudinal_mixed_type_data > > ### ** Examples > > n <- 100 > n_i <- 4 > G <- 2 > timepar <- "mix" > catpar <- "no" > catsubjfix <- TRUE > xin1 <- 1 > Kord <- 5 > Kcat <- 4 > kspec_bi_cat <- FALSE > corr <- matrix(c(1, -0.5, -0.5, -0.4, -0.4, + -0.5, 1, 0.3, 0.4, 0.5, + -0.5, 0.3, 1, 0.2, 0.3, + -0.4, 0.4, 0.2, 1, 0.1, + -0.4, 0.5, 0.3, 0.1, 1), byrow = TRUE, ncol = 5) > sdSigmas <- c(0.5, 0.5, 0.5, 0.5, 0.5) > Sigma <- diag(sdSigmas) > > set.seed(31415) > ldata <- generate_longitudinal_mixed_type_data(n = n, n_i = n_i, + G = G, timepar = timepar, + catpar = catpar, catsubjfix = catsubjfix, + xin1 = xin1, Sigma = Sigma, + Kord = Kord, Kcat = Kcat, kspec_bi_cat = kspec_bi_cat) > data <- ldata$data > head(data) i x j bs1 bs2 bs3 bs4 bs5 f g 1 1 0.1330718 1 0.6395799651 0.1416649 0.00000000 0.00000000 0.0000000 0 2 2 1 0.3357378 2 0.2158566570 0.7253356 0.05880771 0.00000000 0.0000000 0 2 3 1 0.4901114 3 0.0007822799 0.5379900 0.46122776 0.00000000 0.0000000 0 2 4 1 0.9502223 4 0.0000000000 0.0000000 0.01982255 0.33875390 0.6414235 0 2 5 2 0.2356964 1 0.5523042649 0.4444222 0.00000000 0.00000000 0.0000000 1 2 6 2 0.5821669 2 0.0000000000 0.2253436 0.72064519 0.05401118 0.0000000 1 2 b_num b_poi b_bin b_ord b_cat pred_num pred_poi 1 -0.1790080 0.6963244 0.4229566 -0.9811875 -0.3686017 1.0553655 1.4301808 2 -0.1790080 0.6963244 0.4229566 -0.9811875 -0.3686017 1.1209920 1.0248489 3 -0.1790080 0.6963244 0.4229566 -0.9811875 -0.3686017 1.1209920 0.7161017 4 -0.1790080 0.6963244 0.4229566 -0.9811875 -0.3686017 -0.3456657 -0.2041202 5 0.9450053 1.5385980 -0.4384037 -0.9003110 -1.2525827 2.2440233 2.0672053 6 0.9450053 1.5385980 -0.4384037 -0.9003110 -1.2525827 2.1747908 1.3742643 pred_bin pred_ord c_ord1 c_ord2 c_ord3 c_ord4 pred_cat1 pred_cat2 1 1.689100 -0.8816045 -2.5 -1.5 -0.5 0.5 0 0.36525465 2 2.094432 -1.0301563 -2.5 -1.5 -0.5 0.5 0 -0.04007721 3 2.403179 -0.6735240 -2.5 -1.5 -0.5 0.5 0 -0.34882442 4 3.323401 -0.4199414 -2.5 -1.5 -0.5 0.5 0 -1.26904629 5 1.032989 -0.8787346 -2.5 -1.5 -0.5 0.5 0 -0.72397547 6 1.725930 -0.3022002 -2.5 -1.5 -0.5 0.5 0 -1.41691650 pred_cat3 pred_cat4 ynum ypoi ybin yord ycat 1 -1.1024580 -0.3686017 0.4765716 3 0 3 0 2 -0.6971261 -0.3686017 0.6035054 2 1 3 1 3 -0.3883789 -0.3686017 0.9602338 5 1 2 3 4 0.5318429 -0.3686017 -0.8438771 0 1 1 3 5 -1.7811900 -1.2525827 3.6897330 7 0 0 0 6 -1.0882490 -1.2525827 2.5682173 6 1 4 2 > > # The same as the "longitudinal_mixed_type_data" > # which will be used in other examples > data("longitudinal_mixed_type_data") > > > > cleanEx() > nameEx("get_Sigma") > ### * get_Sigma > > flush(stderr()); flush(stdout()) > > ### Name: get_Sigma > ### Title: Extract the m-th Sample of Sigma or sd_num > ### Aliases: get_Sigma get_sd_num > ### Keywords: internal > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### Getting Sigma matrix and sd_num > ###----------------------------------------------------------------------------- > > # We take the last generated value by m = mcmc$iter > > Sigma <- get_Sigma(mcmc$draws[[1]], mcmc$iter, mcmc$settings[[1]], + 1, howsave = mcmc$howsave) > sd_num <- get_sd_num(mcmc$draws[[1]], mcmc$iter, mcmc$settings[[1]], + "ynum", howsave = mcmc$howsave) > > > > > cleanEx() > nameEx("get_scalar_samples") > ### * get_scalar_samples > > flush(stderr()); flush(stdout()) > > ### Name: get_scalar_samples > ### Title: Extract Samples for Specified Scalar Model Parameter > ### Aliases: get_scalar_samples > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### The use of get_scalar_parameter_samples > ###----------------------------------------------------------------------------- > # Finding values for a specific parameter > # beta_num is group-specific, outcome-dependent and is a vector > get_scalar_samples(mcmc, what = "beta_num", gspec = 2, dimspec = 1, yspec = "ynum", + burnin = 0, thin = 1, chains = 1:nchains) $whatLAB [1] "beta_num_ynum(2)[1]" $draws $draws[[1]] chain m y 1 1 1 -0.1821517 2 1 2 -1.0749503 3 1 3 -1.5578674 4 1 4 -1.6833651 5 1 5 -1.4826512 6 1 6 -1.6881707 7 1 7 -1.7857852 8 1 8 -1.5134515 9 1 9 -1.6742443 10 1 10 -1.7111706 11 1 11 -1.9305620 12 1 12 -1.6073320 13 1 13 -1.4496921 14 1 14 -1.5472072 15 1 15 -1.9458926 16 1 16 -1.6677833 17 1 17 -1.7138426 18 1 18 -1.8481824 19 1 19 -1.7093921 20 1 20 -1.7065187 21 1 21 -1.8263730 22 1 22 -1.5706493 23 1 23 -1.8129541 24 1 24 -1.9243241 25 1 25 -1.7763708 26 1 26 -1.8981632 27 1 27 -1.8370715 28 1 28 -1.9635154 29 1 29 -2.1109994 30 1 30 -1.9087961 31 1 31 -2.0990575 32 1 32 -1.8447339 33 1 33 -1.8964339 34 1 34 -1.9195076 35 1 35 -2.0569908 36 1 36 -1.9281394 37 1 37 -1.9810976 38 1 38 -2.0322033 39 1 39 -2.0789760 40 1 40 -2.0618422 41 1 41 -2.0574425 42 1 42 -2.0738753 43 1 43 -2.1536730 44 1 44 -2.2057150 45 1 45 -2.1203210 46 1 46 -2.2545197 47 1 47 -2.0137402 48 1 48 -2.3212723 49 1 49 -2.2269376 50 1 50 -2.2879339 51 1 51 -2.1902054 52 1 52 -2.3106137 53 1 53 -2.5028251 54 1 54 -2.5246570 55 1 55 -2.2577544 56 1 56 -2.1700436 57 1 57 -2.4131847 58 1 58 -2.3571953 59 1 59 -2.2378977 60 1 60 -2.3475428 61 1 61 -2.2543120 62 1 62 -2.1635633 63 1 63 -2.1756123 64 1 64 -2.1724064 65 1 65 -2.2331848 66 1 66 -2.0924107 67 1 67 -2.1497522 68 1 68 -1.9063896 69 1 69 -2.0551016 70 1 70 -1.9897051 71 1 71 -1.9708785 72 1 72 -2.0082704 73 1 73 -1.9195794 74 1 74 -1.9000118 75 1 75 -1.9868041 76 1 76 -1.9906004 77 1 77 -2.1347957 78 1 78 -1.6888703 79 1 79 -1.9989000 80 1 80 -1.9001835 81 1 81 -1.7779559 82 1 82 -2.0940263 83 1 83 -1.8766463 84 1 84 -1.9410448 85 1 85 -2.0647725 86 1 86 -1.8291338 87 1 87 -1.9704232 88 1 88 -1.8004231 89 1 89 -1.8395624 90 1 90 -1.9120369 91 1 91 -1.8547619 92 1 92 -1.6413481 93 1 93 -1.8639969 94 1 94 -1.6714338 95 1 95 -1.7319590 96 1 96 -1.8478753 97 1 97 -1.9425484 98 1 98 -1.9572471 99 1 99 -1.8381383 100 1 100 -1.7922436 $draws[[2]] chain m y 1 2 1 -0.9920102 2 2 2 -1.8894100 3 2 3 -1.8533083 4 2 4 -1.6663912 5 2 5 -2.0559911 6 2 6 -1.6851343 7 2 7 -2.0018056 8 2 8 -1.4069910 9 2 9 -1.8180292 10 2 10 -0.8788125 11 2 11 -0.1680503 12 2 12 3.8115135 13 2 13 2.0720932 14 2 14 -9.4485150 15 2 15 6.2426718 16 2 16 4.7772056 17 2 17 0.2814310 18 2 18 -1.5856915 19 2 19 -0.6070239 20 2 20 9.7159643 21 2 21 10.3325186 22 2 22 -13.5587448 23 2 23 -12.3267377 24 2 24 6.0775629 25 2 25 0.6901656 26 2 26 2.5260215 27 2 27 0.4832765 28 2 28 2.5927580 29 2 29 -14.2668385 30 2 30 -0.8632552 31 2 31 -2.6521110 32 2 32 -3.6033344 33 2 33 1.9886662 34 2 34 6.3577487 35 2 35 10.1629634 36 2 36 13.6321184 37 2 37 3.0886830 38 2 38 -14.5878962 39 2 39 -0.7113308 40 2 40 2.1296652 41 2 41 -5.3613591 42 2 42 -5.9301797 43 2 43 0.9688181 44 2 44 -3.3900185 45 2 45 -1.0024123 46 2 46 1.0755410 47 2 47 4.6103930 48 2 48 -14.6064717 49 2 49 17.3671228 50 2 50 -45.6396393 51 2 51 41.1924698 52 2 52 -7.1822768 53 2 53 -10.5056743 54 2 54 29.5848720 55 2 55 11.9031817 56 2 56 -11.2594377 57 2 57 17.0344477 58 2 58 -0.7288060 59 2 59 15.5352438 60 2 60 10.2245759 61 2 61 -6.5097807 62 2 62 -3.5958345 63 2 63 -5.1221714 64 2 64 12.5719968 65 2 65 -0.3996074 66 2 66 1.0475081 67 2 67 -11.3075322 68 2 68 -4.5520833 69 2 69 -5.6624600 70 2 70 0.8618449 71 2 71 0.3765096 72 2 72 17.8398810 73 2 73 22.0602019 74 2 74 0.8864073 75 2 75 -4.2657284 76 2 76 2.8502522 77 2 77 -0.4182618 78 2 78 10.4375936 79 2 79 37.1695944 80 2 80 -27.1944523 81 2 81 -24.6159446 82 2 82 14.4296098 83 2 83 -34.9928165 84 2 84 -22.7854620 85 2 85 6.4313406 86 2 86 7.9851095 87 2 87 -5.0770003 88 2 88 -27.4630754 89 2 89 -8.9980654 90 2 90 -4.6843915 91 2 91 -9.8010027 92 2 92 -4.7644086 93 2 93 -21.9864953 94 2 94 -4.0119229 95 2 95 37.6004253 96 2 96 -31.0239384 97 2 97 2.5053342 98 2 98 10.3024746 99 2 99 -0.6962095 100 2 100 -4.3300348 > > # beta_num_fix is not group-specific, but outcome-dependent and is a vector > get_scalar_samples(mcmc, what = "beta_num_fix", dimspec = 1, yspec = "ynum", + burnin = 0, thin = 1, chains = 1:nchains) $whatLAB [1] "beta_num_fix_ynum[1]" $draws $draws[[1]] chain m y 1 1 1 0.056382066 2 1 2 0.015708354 3 1 3 0.083341476 4 1 4 -0.091399490 5 1 5 -0.102418483 6 1 6 0.085446426 7 1 7 -0.091535337 8 1 8 -0.176299413 9 1 9 -0.294941877 10 1 10 -0.051658363 11 1 11 -0.023759034 12 1 12 -0.060190667 13 1 13 -0.012536189 14 1 14 -0.127384029 15 1 15 -0.018903674 16 1 16 -0.135211726 17 1 17 -0.095696354 18 1 18 0.044943353 19 1 19 -0.154404292 20 1 20 -0.132577978 21 1 21 -0.195318590 22 1 22 -0.210826336 23 1 23 -0.132602661 24 1 24 -0.048886185 25 1 25 -0.157136882 26 1 26 -0.153253675 27 1 27 -0.197419411 28 1 28 0.088015903 29 1 29 0.013063891 30 1 30 -0.030579113 31 1 31 -0.060099312 32 1 32 0.095594397 33 1 33 0.024788589 34 1 34 -0.276661806 35 1 35 0.013187956 36 1 36 0.076620643 37 1 37 0.082629626 38 1 38 0.210662232 39 1 39 0.069744937 40 1 40 0.043950859 41 1 41 0.014726571 42 1 42 0.108166230 43 1 43 -0.018424293 44 1 44 0.024726619 45 1 45 0.010532865 46 1 46 0.286562290 47 1 47 0.108191182 48 1 48 0.150107059 49 1 49 0.276689012 50 1 50 0.267367034 51 1 51 0.369976986 52 1 52 0.450995066 53 1 53 0.506935252 54 1 54 0.458096368 55 1 55 0.300348259 56 1 56 0.260874673 57 1 57 0.271026323 58 1 58 0.179179624 59 1 59 0.371711349 60 1 60 0.351687374 61 1 61 0.216993364 62 1 62 0.300787010 63 1 63 0.332708510 64 1 64 0.280161042 65 1 65 0.286079882 66 1 66 0.270014561 67 1 67 0.218693998 68 1 68 0.178285574 69 1 69 0.148845860 70 1 70 0.046871865 71 1 71 0.099578801 72 1 72 0.156076730 73 1 73 0.046402814 74 1 74 0.022542723 75 1 75 0.028186536 76 1 76 0.080006877 77 1 77 0.025480852 78 1 78 -0.052631048 79 1 79 0.028969053 80 1 80 -0.048383713 81 1 81 -0.019439388 82 1 82 0.077425303 83 1 83 -0.027572013 84 1 84 -0.106610236 85 1 85 0.098366545 86 1 86 0.044041060 87 1 87 -0.014570153 88 1 88 -0.067101771 89 1 89 -0.123086013 90 1 90 -0.228402637 91 1 91 -0.001130164 92 1 92 -0.082214409 93 1 93 -0.030149010 94 1 94 -0.117219154 95 1 95 -0.052048702 96 1 96 0.048628293 97 1 97 0.004985786 98 1 98 -0.014404552 99 1 99 -0.014440137 100 1 100 -0.108826840 $draws[[2]] chain m y 1 2 1 -0.1490800467 2 2 2 -0.1265458589 3 2 3 0.0137372735 4 2 4 -0.0385051656 5 2 5 -0.1235268876 6 2 6 -0.0835661866 7 2 7 -0.2272682678 8 2 8 0.0331722608 9 2 9 -0.0532180914 10 2 10 0.0724744825 11 2 11 0.1251900036 12 2 12 -0.0343611592 13 2 13 -0.2115520981 14 2 14 -0.1152751878 15 2 15 -0.1212085278 16 2 16 -0.0980688469 17 2 17 -0.2378602556 18 2 18 -0.2012773797 19 2 19 -0.1307528177 20 2 20 -0.3038799517 21 2 21 -0.2292274959 22 2 22 -0.3008451824 23 2 23 -0.2097473428 24 2 24 -0.1098724643 25 2 25 -0.1661883953 26 2 26 -0.2045688699 27 2 27 -0.1350581621 28 2 28 -0.2139710681 29 2 29 -0.0835640306 30 2 30 -0.0530896384 31 2 31 -0.1980231366 32 2 32 -0.0996167909 33 2 33 -0.3060982712 34 2 34 -0.1194157261 35 2 35 -0.2160733876 36 2 36 -0.1125553147 37 2 37 -0.0003015189 38 2 38 0.0012420206 39 2 39 -0.0439246859 40 2 40 -0.1020412409 41 2 41 -0.2091463637 42 2 42 -0.0715206769 43 2 43 -0.1015977784 44 2 44 -0.1196099126 45 2 45 -0.2430528700 46 2 46 -0.2017274243 47 2 47 0.0524406190 48 2 48 -0.2235689966 49 2 49 0.0300013122 50 2 50 -0.1233746382 51 2 51 -0.1633385526 52 2 52 -0.0556078010 53 2 53 -0.2357474414 54 2 54 -0.1296186024 55 2 55 -0.2490102125 56 2 56 0.0140304856 57 2 57 -0.0027916499 58 2 58 0.0042955054 59 2 59 0.0213419421 60 2 60 -0.0148613599 61 2 61 -0.1415509450 62 2 62 0.0717514034 63 2 63 0.0501233912 64 2 64 -0.0517161751 65 2 65 -0.0858405580 66 2 66 0.1471145692 67 2 67 -0.1300273680 68 2 68 -0.0700179429 69 2 69 -0.0117356098 70 2 70 -0.0975417007 71 2 71 0.1470460051 72 2 72 -0.0855899189 73 2 73 -0.0590612383 74 2 74 0.0957030147 75 2 75 0.0879531224 76 2 76 0.0863412481 77 2 77 0.0557982196 78 2 78 0.0005531539 79 2 79 -0.0792156213 80 2 80 -0.1400831430 81 2 81 0.0831211734 82 2 82 -0.1274162990 83 2 83 0.1795067130 84 2 84 -0.0542354657 85 2 85 -0.0228909621 86 2 86 0.1439690561 87 2 87 -0.1732318700 88 2 88 0.0630146324 89 2 89 0.0221884370 90 2 90 0.0534312468 91 2 91 0.1180061660 92 2 92 0.1013701165 93 2 93 -0.1160116571 94 2 94 -0.0192229104 95 2 95 0.3314480125 96 2 96 0.1895331965 97 2 97 0.0161650723 98 2 98 -0.0850962436 99 2 99 0.0499056884 100 2 100 0.0975755163 > > mcmc$varying["InvSigma"] InvSigma FALSE > # InvSigma is not group-specific, not outcome-dependent, but is a symmetric matrix > # only elements [i,j] where i<=j are allowed > get_scalar_samples(mcmc, what = "InvSigma", dimspec = c(1,1), + burnin = 50, thin = 1, chains = 1:nchains) $whatLAB [1] "InvSigma[1,1]" $draws $draws[[1]] chain m y 1 1 51 5.010657 2 1 52 6.079587 3 1 53 4.742330 4 1 54 5.406974 5 1 55 4.615650 6 1 56 5.657607 7 1 57 5.337996 8 1 58 4.800156 9 1 59 3.875317 10 1 60 3.680625 11 1 61 3.922956 12 1 62 5.403393 13 1 63 5.864182 14 1 64 5.129648 15 1 65 5.062952 16 1 66 4.501246 17 1 67 6.258671 18 1 68 6.874044 19 1 69 6.010603 20 1 70 7.443732 21 1 71 6.422221 22 1 72 6.302568 23 1 73 8.167545 24 1 74 6.069157 25 1 75 6.947866 26 1 76 7.048578 27 1 77 5.690113 28 1 78 5.272439 29 1 79 4.684365 30 1 80 3.843883 31 1 81 5.559330 32 1 82 6.236654 33 1 83 7.199676 34 1 84 9.627291 35 1 85 7.055319 36 1 86 7.011751 37 1 87 6.786937 38 1 88 7.068169 39 1 89 6.130976 40 1 90 5.492750 41 1 91 5.726918 42 1 92 5.222586 43 1 93 5.560445 44 1 94 7.262328 45 1 95 7.922720 46 1 96 8.733655 47 1 97 8.548212 48 1 98 6.957171 49 1 99 7.912590 50 1 100 8.710421 $draws[[2]] chain m y 1 2 51 6.783681 2 2 52 6.873907 3 2 53 8.644772 4 2 54 6.371937 5 2 55 6.150158 6 2 56 5.895592 7 2 57 7.155248 8 2 58 6.534126 9 2 59 5.999215 10 2 60 6.998144 11 2 61 5.988311 12 2 62 7.126327 13 2 63 9.292421 14 2 64 7.204281 15 2 65 6.014362 16 2 66 6.345779 17 2 67 8.206819 18 2 68 7.975261 19 2 69 7.018775 20 2 70 7.205668 21 2 71 7.037322 22 2 72 6.728134 23 2 73 10.297760 24 2 74 10.053676 25 2 75 8.326974 26 2 76 9.193924 27 2 77 10.631493 28 2 78 8.137134 29 2 79 11.256629 30 2 80 12.488138 31 2 81 13.015820 32 2 82 13.397619 33 2 83 10.252827 34 2 84 9.328153 35 2 85 8.985554 36 2 86 11.278020 37 2 87 7.826638 38 2 88 5.977572 39 2 89 7.610527 40 2 90 8.263381 41 2 91 7.574367 42 2 92 7.553007 43 2 93 7.617578 44 2 94 6.649109 45 2 95 8.580651 46 2 96 6.563565 47 2 97 7.056496 48 2 98 6.522144 49 2 99 6.061838 50 2 100 7.847659 > > # corSigma is not group-specific, not outcome-dependent, but is a symmetric matrix without diagonal > # only elements [i,j] where i get_scalar_samples(mcmc, what = "corSigma", dimspec = c(1,2), + burnin = 50, thin = 10, chains = 1:nchains) $whatLAB [1] "corSigma[1,2]" $draws $draws[[1]] chain m y 1 1 51 -0.6139568 2 1 61 -0.2589201 3 1 71 -0.6093966 4 1 81 -0.4024001 5 1 91 -0.4840080 $draws[[2]] chain m y 1 2 51 -0.4018280 2 2 61 -0.4562352 3 2 71 -0.4751055 4 2 81 -0.3543824 5 2 91 -0.5109642 > > > > > cleanEx() > nameEx("longitudinal_mixed_type_data") > ### * longitudinal_mixed_type_data > > flush(stderr()); flush(stdout()) > > ### Name: longitudinal_mixed_type_data > ### Title: A Simulated Dataset of Longitudinal Mixed-Type Data > ### Aliases: longitudinal_mixed_type_data > ### Keywords: longitudinal_mixed_type_data > > ### ** Examples > > data(longitudinal_mixed_type_data) > summary(longitudinal_mixed_type_data) i x j bs1 Min. : 1.00 Min. :0.0006543 Min. :1.00 Min. :0.000000 1st Qu.: 25.75 1st Qu.:0.2549268 1st Qu.:1.75 1st Qu.:0.000000 Median : 50.50 Median :0.4745111 Median :2.50 Median :0.004766 Mean : 50.50 Mean :0.4888765 Mean :2.50 Mean :0.168857 3rd Qu.: 75.25 3rd Qu.:0.7492697 3rd Qu.:3.25 3rd Qu.:0.334331 Max. :100.00 Max. :0.9984985 Max. :4.00 Max. :0.666642 bs2 bs3 bs4 bs5 Min. :0.000e+00 Min. :0.0000000 Min. :0.0000 Min. :0.000e+00 1st Qu.:2.570e-06 1st Qu.:0.0001401 1st Qu.:0.0000 1st Qu.:0.000e+00 Median :1.761e-01 Median :0.1099994 Median :0.0000 Median :0.000e+00 Mean :2.783e-01 Mean :0.2323496 Mean :0.1565 Mean :8.122e-02 3rd Qu.:5.574e-01 3rd Qu.:0.4504682 3rd Qu.:0.2946 3rd Qu.:5.300e-07 Max. :7.500e-01 Max. :0.7499922 Max. :0.6666 Max. :9.880e-01 f g b_num b_poi b_bin 0:180 Min. :1.00 Min. :-1.46314 Min. :-1.20963 Min. :-1.2853 1:220 1st Qu.:1.00 1st Qu.:-0.32161 1st Qu.:-0.15604 1st Qu.:-0.3925 Median :1.00 Median :-0.01787 Median : 0.09244 Median :-0.1208 Mean :1.49 Mean :-0.01662 Mean : 0.08911 Mean :-0.0169 3rd Qu.:2.00 3rd Qu.: 0.28918 3rd Qu.: 0.42858 3rd Qu.: 0.3041 Max. :2.00 Max. : 0.98786 Max. : 1.43231 Max. : 1.7092 b_ord b_cat pred_num pred_poi Min. :-1.479798 Min. :-1.06771 Min. :-2.5579 Min. :-2.05978 1st Qu.:-0.290580 1st Qu.:-0.27209 1st Qu.:-1.3022 1st Qu.:-0.45236 Median : 0.041163 Median : 0.03408 Median :-0.2868 Median : 0.11042 Mean : 0.006223 Mean : 0.02762 Mean :-0.1670 Mean : 0.09589 3rd Qu.: 0.372597 3rd Qu.: 0.35128 3rd Qu.: 1.0693 3rd Qu.: 0.67256 Max. : 1.135763 Max. : 1.22465 Max. : 2.2541 Max. : 2.18586 pred_bin pred_ord c_ord1 c_ord2 Min. :-1.7337 Min. :-1.45491 Min. :-2.50 Min. :-1.50 1st Qu.:-0.1493 1st Qu.:-0.06266 1st Qu.:-2.50 1st Qu.:-1.50 Median : 0.8323 Median : 0.32602 Median :-1.50 Median :-0.50 Mean : 0.9409 Mean : 0.29124 Mean :-1.99 Mean :-0.99 3rd Qu.: 1.9853 3rd Qu.: 0.69869 3rd Qu.:-1.50 3rd Qu.:-0.50 Max. : 4.2716 Max. : 1.45371 Max. :-1.50 Max. :-0.50 c_ord3 c_ord4 pred_cat1 pred_cat2 Min. :-0.50 Min. :0.50 Min. :0 Min. :-1.95098 1st Qu.:-0.50 1st Qu.:0.50 1st Qu.:0 1st Qu.:-0.52434 Median : 0.50 Median :1.50 Median :0 Median : 0.04830 Mean : 0.01 Mean :1.01 Mean :0 Mean : 0.03441 3rd Qu.: 0.50 3rd Qu.:1.50 3rd Qu.:0 3rd Qu.: 0.65444 Max. : 0.50 Max. :1.50 Max. :0 Max. : 1.82601 pred_cat3 pred_cat4 ynum ypoi Min. :-1.477781 Min. :-1.06771 Min. :-3.3721 Min. :0.000 1st Qu.:-0.511948 1st Qu.:-0.27209 1st Qu.:-1.3052 1st Qu.:0.000 Median : 0.004071 Median : 0.03408 Median :-0.3548 Median :1.000 Mean : 0.020832 Mean : 0.02762 Mean :-0.1667 Mean :1.505 3rd Qu.: 0.519897 3rd Qu.: 0.35128 3rd Qu.: 1.0078 3rd Qu.:2.000 Max. : 1.998756 Max. : 1.22465 Max. : 4.7516 Max. :9.000 ybin yord ycat Min. :0.0000 0: 57 0: 77 1st Qu.:0.0000 1: 55 1:114 Median :1.0000 2: 59 2:122 Mean :0.6375 3: 84 3: 87 3rd Qu.:1.0000 4:145 Max. :1.0000 > > > > cleanEx() > nameEx("nice_nrow_ncol") > ### * nice_nrow_ncol > > flush(stderr()); flush(stdout()) > > ### Name: nice_nrow_ncol > ### Title: Determine Optimal Matrix Dimensions Given the Number of Cells > ### Aliases: nice_nrow_ncol > > ### ** Examples > > nice_nrow_ncol(10) [1] 2 5 > nice_nrow_ncol(11) [1] 3 4 > nice_nrow_ncol(15) [1] 3 5 > nice_nrow_ncol(15, increasing = FALSE) [1] 5 3 > > # (2, 17) does not fulfill the condition on maxratio > nice_nrow_ncol(34, maxratio = 3) [1] 5 7 > > # (2, 17) fulfills the condition on maxratio > nice_nrow_ncol(34, maxratio = 10) [1] 2 17 > > # ceiling(sqrt(34)) = 6 but 6+5=11 < 17 and pair (2, 17) is not even considered > nice_nrow_ncol(34, maxsteps = 5, maxratio = 10) [1] 5 7 > nice_nrow_ncol(34, maxsteps = 11, maxratio = 10) [1] 5 7 > nice_nrow_ncol(34, maxsteps = 12, maxratio = 10) [1] 2 17 > > > > cleanEx() > nameEx("plot.clustglmm") > ### * plot.clustglmm > > flush(stderr()); flush(stdout()) > > ### Name: plot.clustglmm > ### Title: Plot the Output of 'clustGLMM' > ### Aliases: plot.clustglmm > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### Using plot() function on clustglmm object > ###----------------------------------------------------------------------------- > > # traceplots by default > plot(mcmc) > plot(mcmc, "Gplus") > plot(mcmc, "beta_num", burnin=10, thin=2, chains=c(1)) > > # change the plot type > plot(mcmc, "w", "ACF") > plot(mcmc, "sdSigma", "ECDF") > plot(mcmc, "corSigma", "kerneldensity") > plot(mcmc, "beta_bin", "clusters_kerneldensity") > plot(mcmc, "beta_ord", "clusters_ECDF") > > > > > cleanEx() > nameEx("plot_cat_vs_x_grouped") > ### * plot_cat_vs_x_grouped > > flush(stderr()); flush(stdout()) > > ### Name: plot_cat_vs_x_grouped > ### Title: Plot Clustered Longitudinal (Panel) Data > ### Aliases: plot_cat_vs_x_grouped plot_num_vs_x_grouped > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### Clustering based on not post-processed data (using sampled indicators) > ###----------------------------------------------------------------------------- > ### Take the sampled U indicators > threshold <- 0.5 # if not exceeded, unit remains unclassified > > # posterior mode of Gplus=number of nonemtpy components > mcmc$modeGplus [1] 2 3 > > # labels of non-empty clusters in each chain > mcmc$clusters [[1]] [1] 2 3 [[2]] [1] 1 3 4 > > # clustering based on sampled indicators > myclustering <- mcmc$clustering > > # the highest estimated clustering probability among all clusters > mcmc$certainty [,1] [,2] 1 1.00 0.86 2 0.96 0.88 3 1.00 0.98 4 0.97 0.99 5 1.00 1.00 6 0.97 0.83 7 0.99 0.76 8 0.99 1.00 9 0.98 0.94 10 0.86 0.81 11 0.93 0.78 12 1.00 0.99 13 0.98 0.85 14 0.97 0.83 15 0.99 0.95 16 1.00 0.99 17 0.99 0.51 18 1.00 0.97 19 0.99 0.94 20 0.98 1.00 21 0.56 0.96 22 0.96 0.99 23 0.98 0.76 24 0.98 0.96 25 0.99 0.85 26 0.99 0.94 27 0.99 1.00 28 0.99 0.98 29 0.71 0.78 30 0.98 0.87 31 0.99 1.00 32 0.96 0.78 33 0.98 0.77 34 0.98 0.82 35 0.99 0.88 36 0.97 0.89 37 0.99 0.91 38 0.97 0.94 39 1.00 0.78 40 0.98 0.94 41 0.99 0.96 42 0.95 0.53 43 1.00 1.00 44 0.97 0.93 45 0.99 0.97 46 0.99 0.89 47 0.94 0.95 48 0.99 0.94 49 0.98 0.89 50 1.00 0.55 51 0.97 0.82 52 0.99 0.74 53 1.00 0.99 54 1.00 0.70 55 1.00 0.94 56 0.98 0.54 57 1.00 0.99 58 0.99 0.96 59 0.99 0.97 60 1.00 0.98 61 1.00 0.74 62 0.99 0.93 63 1.00 0.97 64 1.00 0.96 65 0.99 1.00 66 1.00 0.96 67 0.99 1.00 68 0.99 0.59 69 1.00 0.92 70 0.98 0.92 71 0.98 0.89 72 0.96 0.57 73 0.98 0.94 74 0.98 1.00 75 0.91 0.72 76 0.93 0.99 77 0.98 0.86 78 1.00 0.64 79 1.00 0.95 80 1.00 0.58 81 1.00 1.00 82 0.71 0.93 83 0.98 0.98 84 0.96 0.52 85 1.00 0.78 86 0.97 0.89 87 0.98 0.99 88 0.94 0.97 89 0.99 1.00 90 0.99 1.00 91 1.00 0.60 92 0.99 0.96 93 0.75 0.97 94 0.97 0.99 95 0.99 0.64 96 0.98 0.97 97 0.98 0.98 98 1.00 0.99 99 1.00 0.98 100 1.00 0.96 > > # units with frequency ratio smaller than chosen threshold remain unclassified (group 0) > myclustering[mcmc$certainty < threshold] <- 0 > clusters <- list() > > # proposed clustering by each chain separately > for(ch in 1:mcmc$nchains){ + longitudinal_mixed_type_data[,paste0("clustering",ch)] <- + myclustering[longitudinal_mixed_type_data[,id],ch] + longitudinal_mixed_type_data[,paste0("certainty",ch)] <- + mcmc$certainty[longitudinal_mixed_type_data[,id],ch] + } > > data1 <- longitudinal_mixed_type_data[longitudinal_mixed_type_data$j==1,] > # Confusion matrices for each chain separately: > table(data1$clustering1, data1$g) 1 2 2 49 0 3 2 49 > # We can also see the suitable permutation for labels > > ###----------------------------------------------------------------------------- > ### Plotting the resulting clustering > ###----------------------------------------------------------------------------- > > # Plotting numeric outcomes > plot_num_vs_x_grouped(longitudinal_mixed_type_data, y = "ynum", x = "x", + group = "g", id = "i", units = 1:mcmc$n) > > plot_num_vs_x_grouped(longitudinal_mixed_type_data, y = "ynum", x = "x", + group = "clustering1", id = "i", units = 1:mcmc$n) > > # Plotting binary, ordinal, categorical outcomes > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "ybin", x = "x", + group = "g") > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "ybin", x = "x", + group = "g", reverse = TRUE) > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "ybin", x = "x", + group = "clustering1") > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "yord", x = "x", + group = "g", reverse = TRUE) > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "yord", x = "x", + group = "g", reverse = FALSE) > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "yord", x = "x", + group = "clustering1") > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "ycat", x = "x", + group = "g") > > plot_cat_vs_x_grouped(longitudinal_mixed_type_data, y = "ycat", x = "x", + group = "clustering1") > > > > cleanEx() > nameEx("plot_diagnostics") > ### * plot_diagnostics > > flush(stderr()); flush(stdout()) > > ### Name: plot_diagnostics > ### Title: Plot MCMC Samples from 'clustGLMM' > ### Aliases: plot_diagnostics plot_ACF plot_ECDF plot_kerneldensity > ### plot_traceplots plot_ng_trace_chain_split plot_ACF_param > ### plot_ECDF_param plot_kerneldensity_param plot_traceplots_param > ### plot_clusters plot_clusters_ECDF_param > ### plot_clusters_kerneldensity_param > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > plot(mcmc) > plot(mcmc, ng_trace_chain_split=FALSE) > > ###----------------------------------------------------------------------------- > ### Creating plots > ###----------------------------------------------------------------------------- > > ## Traceplots of number of non-empty clusters > # Plotting with defaults values: > # thin = 1, burnin = 0, chains = 1:mcmc$nchains > plot_traceplots(mcmc = mcmc, what = "Gplus") > > ## Traceplots of number of observations in cluster 1 > plot_traceplots(mcmc = mcmc, what = "ng", gspec = 1) > > # Omitting the burn-in-period > plot_traceplots(mcmc = mcmc, what = "ng", gspec = 1, burnin = 20) > > # Thinned plots > plot_traceplots(mcmc = mcmc, what = "ng", gspec = 1, burnin = 20, thin = 5) > > ## First fixed beta coefficient for the first numerical outcome > plot_ACF(mcmc = mcmc, what = "beta_num_fix", yspec = mcmc$Nums[1], dimspec = 1) > plot_ECDF(mcmc = mcmc, what = "beta_num_fix", yspec = mcmc$Nums[1], dimspec = 1) > plot_kerneldensity(mcmc = mcmc, what = "beta_num_fix", yspec = mcmc$Nums[1], + dimspec = 1, dolegend = TRUE) > plot_traceplots(mcmc = mcmc, what = "beta_num_fix", yspec = mcmc$Nums[1], + dimspec = 1) > plot_diagnostics(mcmc = mcmc, what = "beta_num_fix", yspec = mcmc$Nums[1], dimspec = 1) > > ## Correlation matrix between the random effects > # True correlation matrix used for generating the data > corr <- matrix(c(1, -0.5, -0.5, -0.4, -0.4, + -0.5, 1, 0.3, 0.4, 0.5, + -0.5, 0.3, 1, 0.2, 0.3, + -0.4, 0.4, 0.2, 1, 0.1, + -0.4, 0.5, 0.3, 0.1, 1), byrow = TRUE, ncol = 5) > > par(mfrow = c(mcmc$totnran-1, mcmc$totnran-1), mar = c(4, 4, 1, 1)) > for(i in 1:(mcmc$totnran-1)){ + for(j in 2:(mcmc$totnran)){ + if(i < j){ + plot_traceplots(mcmc = mcmc, what = "corSigma", + dimspec = c(i, j), + labcex = 0.6) + abline(h = corr[i,j], col = "black", lty = 2) + }else{ + plot(x = c(0, 1), y = c(0, 1), type = "n", xlab = "", ylab = "", + xaxt = "n", yaxt = "n", bty = "n") + } + } + } > # or simply use > plot_traceplots_param(mcmc, "corSigma") > # but no true value displayed... > > ## Possible what arguments: > # "_param" - plots everything tied to the given what parameter > plot_traceplots_param(mcmc, "Gplus", thin = 5) > plot_traceplots_param(mcmc, "e0", thin = 5) > plot_traceplots_param(mcmc, "ng", thin = 5) > plot_traceplots_param(mcmc, "w", thin = 5) > plot_traceplots_param(mcmc, "sdSigma", thin = 5) > plot_traceplots_param(mcmc, "corSigma", thin = 5) > plot_traceplots_param(mcmc, "Sigma", thin = 5) > plot_traceplots_param(mcmc, "InvSigma", thin = 5) > plot_traceplots_param(mcmc, "prec_num", thin = 5) > plot_traceplots_param(mcmc, "beta_num_fix", thin = 5) > plot_traceplots_param(mcmc, "beta_num", thin = 5) > plot_traceplots_param(mcmc, "beta_poi_fix", thin = 5) > plot_traceplots_param(mcmc, "beta_poi", thin = 5) > plot_traceplots_param(mcmc, "beta_bin_fix", thin = 5) > plot_traceplots_param(mcmc, "beta_bin", thin = 5) > plot_traceplots_param(mcmc, "beta_ord_fix", thin = 5) > plot_traceplots_param(mcmc, "beta_ord", thin = 5) > plot_traceplots_param(mcmc, "c_ord", thin = 5) > plot_traceplots_param(mcmc, "beta_cat_fix", thin = 5) > plot_traceplots_param(mcmc, "beta_cat", thin = 5) > plot_traceplots_param(mcmc, "loglik", thin = 5) > > ## Other "_param" versions for different types of plots > plot_kerneldensity_param(mcmc, "beta_num") > plot_ECDF_param(mcmc, "prec_num") > plot_ACF_param(mcmc, "w") > > ## Comparing different cluster-specific parameters > ## We recommend to do it for chains separately > ch <- 1 > TAB <- table(mcmc$last[[ch]]$U) > nonempty <- as.numeric(names(TAB)[which(TAB>0)]) > # non-empty clusters decided based on last sampled values > # by default, mcmc$clusters (based on all iterations) is taken > > neff <- mcmc$ngrp[[mcmc$Nums[1]]] > oldpar <- par(mfrow = c(length(mcmc$Nums), neff), mar = c(4, 4, 1, 1)) > > for(y in mcmc$Nums){ + for(i in 1:neff){ + plot_clusters(mcmc = mcmc, what = "beta_num", + yspec = y, dimspec = i, whichg = nonempty, + setparmfrow = FALSE, chains = ch, + doECDF = FALSE) + # Now you can add anything to the plot + # e.g. true values, etc. + } + } > par(oldpar) > > # or simply use > plot_clusters_kerneldensity_param(mcmc = mcmc, what = "beta_num", chains = c(ch)) > # where cluster labels are taken from mcmc$clusters > > > > > graphics::par(get("par.postscript", pos = 'CheckExEnv')) > cleanEx() > nameEx("post_processing") > ### * post_processing > > flush(stderr()); flush(stdout()) > > ### Name: post_processing > ### Title: Post-process the Chains Sampled with 'clustGLMM' > ### Aliases: post_processing permute_cluster_labels > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 200, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### Post-processing the sampled chains > ###----------------------------------------------------------------------------- > > ### First run the function post_processing > # takes some time with iter large.... > set.seed(12345) > mcmc <- post_processing(mcmc) > mcmc ###------------------------------------------### ### Post-processed MCMC samples of clustGLMM ### ###------------------------------------------### ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- The new number of components for this chain: $G[1] = 2. We now have components: 1, 2. Number of iterations with 2 components: 175 (87.50 %) Out of them, 0 (0.00 %) did not lead to a permutation when using k-means, these g-specific parameters are replaced with NA. Therefore, 175 (100.00 %) iterations have been permuted and aligned. These are now eligible for the analysis. ----------------------------------------------------------------------- Chain 2 ----------------------------------------------------------------------- The new number of components for this chain: $G[2] = 2. We now have components: 1, 2. Number of iterations with 2 components: 170 (85.00 %) Out of them, 0 (0.00 %) did not lead to a permutation when using k-means, these g-specific parameters are replaced with NA. Therefore, 170 (100.00 %) iterations have been permuted and aligned. These are now eligible for the analysis. > summary(mcmc) Cannot coerce to mcmc.list because of different number of variables in each chain. Only a list of mcmc objects is returned, apply summary(), etc. only per chain. ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Iterations = 1:175 Thinning interval = 1 Number of chains = 1 Sample size per chain = 175 Summary of the parameter estimates ----------------------------------------------------------------------- Cluster-invariant parameters: 2.5% 25% 50% Mean beta_num_fix_ynum[1] -0.16139815 -0.023242246 0.055674805 0.066084901 beta_poi_fix_ypoi[1] -0.22957699 -0.092695368 -0.008169424 -0.002178434 beta_bin_fix_ybin[1] -1.23503586 -0.881235987 -0.681843587 -0.689683178 beta_ord_fix_yord[1] 0.40619464 0.705118488 0.705118488 0.695018459 beta_cat_fix_ycat[1,1] -0.50888633 -0.234864870 -0.048742734 -0.050944652 beta_cat_fix_ycat[1,2] -0.44801446 -0.044827121 0.149671115 0.191619237 beta_cat_fix_ycat[1,3] -0.82920318 -0.550717278 -0.339534407 -0.341965445 InvSigma[1,1] 3.03154461 5.673860196 7.469078377 8.082660432 InvSigma[1,2] 0.59446248 3.191498875 4.300699902 5.201354627 InvSigma[2,2] 5.42829751 8.163124206 10.215669437 10.752473465 InvSigma[1,3] -1.08502878 -0.478454940 -0.269232132 -0.308845001 InvSigma[2,3] -1.72865696 -0.588438676 -0.295900200 -0.320597854 InvSigma[3,3] 0.20670506 0.388125296 0.551124024 0.606033074 InvSigma[1,4] -1.19829872 -0.419706649 -0.017081352 0.120351347 InvSigma[2,4] -2.19449283 -1.104733817 -0.520507622 -0.544262494 InvSigma[3,4] -0.68079482 -0.369937779 -0.258724953 -0.274048122 InvSigma[4,4] 1.18260465 1.534416355 1.923581814 2.032156540 InvSigma[1,5] -1.70609979 -1.018428437 -0.498249573 -0.581653132 InvSigma[2,5] -1.82476128 -1.069681865 -0.716428395 -0.764648164 InvSigma[3,5] -0.32393079 -0.146078028 -0.067661553 -0.074050114 InvSigma[4,5] -0.39286014 -0.184708999 -0.050690848 -0.049155878 InvSigma[5,5] 0.16745146 0.448349156 0.629782547 0.599305416 Sigma[1,1] 0.15934725 0.188072452 0.230211053 0.242985135 Sigma[1,2] -0.17641521 -0.133081657 -0.107521191 -0.106899288 Sigma[2,2] 0.12051706 0.157767931 0.184549303 0.190367246 Sigma[1,3] -0.22811904 -0.047531824 0.034455905 0.047162151 Sigma[2,3] -0.13216996 0.013606928 0.101371006 0.112918389 Sigma[3,3] 0.97680411 1.559966883 2.428037345 2.718319726 Sigma[1,4] -0.20786942 -0.102556856 -0.024322885 -0.029124817 Sigma[2,4] -0.12935968 0.017505477 0.068550553 0.064009280 Sigma[3,4] -0.04024355 0.222201050 0.354705788 0.361877950 Sigma[4,4] 0.43709154 0.564626026 0.666177792 0.687383641 Sigma[1,5] -0.28488447 -0.092739225 0.041750586 0.039285301 Sigma[2,5] -0.09996031 0.057460543 0.145381793 0.164221531 Sigma[3,5] -0.34609623 0.211689348 0.464426194 0.549019849 Sigma[4,5] -0.43154882 0.003731816 0.116123159 0.107774181 Sigma[5,5] 1.41965542 1.823536921 2.258654744 2.662266630 sdSigma[1] 0.39918322 0.433672792 0.479803140 0.488505800 sdSigma[2] 0.34715105 0.397200114 0.429592020 0.433458131 sdSigma[3] 0.98833338 1.248983677 1.558216078 1.598715392 sdSigma[4] 0.66112502 0.751415981 0.816197153 0.823163163 sdSigma[5] 1.19146751 1.350383989 1.502882146 1.592280133 corSigma[1,2] -0.76164588 -0.616785120 -0.531844142 -0.512947579 corSigma[1,3] -0.24273415 -0.065748919 0.055096757 0.056626203 corSigma[2,3] -0.18095520 0.028032101 0.164145345 0.157692710 corSigma[1,4] -0.51774780 -0.259731904 -0.061995566 -0.078348660 corSigma[2,4] -0.31903075 0.046763088 0.198478757 0.187669512 corSigma[3,4] -0.02569359 0.189942110 0.287598250 0.276541012 corSigma[1,5] -0.30715107 -0.118101517 0.049908852 0.071589073 corSigma[2,5] -0.15027926 0.104435682 0.241976164 0.231384134 corSigma[3,5] -0.12954277 0.112785832 0.211278793 0.199109109 corSigma[4,5] -0.21775159 0.002516380 0.098469887 0.091486731 75% 97.5% beta_num_fix_ynum[1] 0.129501053 0.36357562 beta_poi_fix_ypoi[1] 0.070638884 0.27208077 beta_bin_fix_ybin[1] -0.516568422 -0.05540163 beta_ord_fix_yord[1] 0.705118488 0.95531074 beta_cat_fix_ycat[1,1] 0.157406598 0.33666284 beta_cat_fix_ycat[1,2] 0.456565794 0.76095207 beta_cat_fix_ycat[1,3] -0.180603558 0.21512867 InvSigma[1,1] 9.643678837 16.41537303 InvSigma[1,2] 6.516346458 14.14870338 InvSigma[2,2] 12.791328074 19.25933814 InvSigma[1,3] -0.112233028 0.39433090 InvSigma[2,3] 0.078833647 0.60731578 InvSigma[3,3] 0.804087269 1.24396965 InvSigma[1,4] 0.642650051 1.93696667 InvSigma[2,4] 0.074162330 1.08456858 InvSigma[3,4] -0.138919648 0.05184708 InvSigma[4,4] 2.362883573 3.71712425 InvSigma[1,5] -0.157093687 0.23150270 InvSigma[2,5] -0.381163943 0.05601091 InvSigma[3,5] 0.007172334 0.13534404 InvSigma[4,5] 0.083502698 0.30810101 InvSigma[5,5] 0.749352623 1.00313777 Sigma[1,1] 0.279771547 0.41457844 Sigma[1,2] -0.088381450 -0.03348088 Sigma[2,2] 0.220263217 0.29632147 Sigma[1,3] 0.113667625 0.42691825 Sigma[2,3] 0.211831443 0.36635161 Sigma[3,3] 3.562394124 5.85958597 Sigma[1,4] 0.031566006 0.16603854 Sigma[2,4] 0.124443768 0.23628298 Sigma[3,4] 0.513408340 0.78918317 Sigma[4,4] 0.793642457 1.08386701 Sigma[1,5] 0.174058739 0.37956219 Sigma[2,5] 0.273697495 0.48655587 Sigma[3,5] 0.793763121 1.84580015 Sigma[4,5] 0.228170121 0.52402138 Sigma[5,5] 2.869422703 6.90953502 sdSigma[1] 0.528934326 0.64387381 sdSigma[2] 0.469322048 0.54432586 sdSigma[3] 1.887416624 2.42065817 sdSigma[4] 0.890865937 1.04108929 sdSigma[5] 1.693917789 2.62822536 corSigma[1,2] -0.444532399 -0.13681139 corSigma[1,3] 0.179262079 0.33583631 corSigma[2,3] 0.303397909 0.48369245 corSigma[1,4] 0.081054412 0.35039371 corSigma[2,4] 0.350998874 0.59020244 corSigma[3,4] 0.378725575 0.52305288 corSigma[1,5] 0.274521482 0.48752481 corSigma[2,5] 0.379610187 0.60625644 corSigma[3,5] 0.305281684 0.48370791 corSigma[4,5] 0.190373137 0.35398681 Clustering-related parameters: 2.5% 25% 50% Mean 75% 97.5% Gplus 2.000000000 2.000000000 2.00000000 2.00000000 2.00000000 2.00000000 e0 0.003230175 0.007691305 0.01712992 0.02159129 0.02868703 0.06191258 w(1) 0.421739392 0.475447171 0.50700034 0.50966658 0.54082688 0.60216874 w(2) 0.397826236 0.458942820 0.49290573 0.48984379 0.52451834 0.57739807 > > # All plotting functions should work even with these post-processed draws > plot(mcmc, "beta_num", "clusters_kerneldensity", chains=1:nchains) > > ### Additionally permute so that the meaning of the number of clusters > ### is kept the same across all chains > > ## first we have to recognize which chain has which meaning > neff <- mcmc$ngrp[["ynum"]] > oldpar <- par(mfrow = c(nchains,neff), mar = c(4,4,1,1)) > for(ch in 1:nchains){ + TAB <- table(mcmc$last[[ch]]$U) + nonempty <- as.numeric(names(TAB)[which(TAB>0)]) + + for(i in 1:neff){ + plot_clusters(mcmc = mcmc, what = "beta_num", + yspec = "ynum", dimspec = i, whichg = nonempty, + setparmfrow = FALSE, chains = ch, + doECDF = FALSE) + } + } > par(oldpar) > > ## confusion matrices with the true labelling > for(ch in 1:mcmc$nchains){ + longitudinal_mixed_type_data[,paste0("clustering",ch)] <- + mcmc$clustering[longitudinal_mixed_type_data[,id],ch] + } > > data1 <- longitudinal_mixed_type_data[longitudinal_mixed_type_data$j==1,] > table(data1$clustering1, data1$g) 1 2 1 2 49 2 49 0 > table(data1$clustering2, data1$g) 1 2 1 50 0 2 1 49 > > > ### Example how to change the permutation so that results across chains align > ### + align also with the true labelling within the given data > perm <- list() > perm[[1]] <- c(2, 1) # change if needed > perm[[2]] <- c(1, 2) # change if needed > > # function to permute meaning of cluster labels in mcmc according to perm > mcmc1 <- permute_cluster_labels(mcmc, perm) > > # If perm is not specified, > # Hungarian algorithm matches the labelling of other chains to chain number 1 > mcmc2 <- permute_cluster_labels(mcmc) Cannot coerce to mcmc.list because of different number of variables in each chain. Only a list of mcmc objects is returned, apply summary(), etc. only per chain. > # which in this case is different from the true labelling in data > > > > ###----------------------------------------------------------------------------- > ### Plotting post-processed chains > ###----------------------------------------------------------------------------- > # Notice that now there are only modeGplus clusters and not original G > > plot(mcmc1, "w", "traceplots", thin = 10) > plot(mcmc1, "w", "kerneldensity") > plot(mcmc1, "beta_num", "clusters_kerneldensity") > plot(mcmc1, "beta_poi", "clusters_kerneldensity") > plot(mcmc1, "beta_bin", "clusters_kerneldensity") > plot(mcmc1, "beta_ord", "clusters_kerneldensity") > plot(mcmc1, "beta_cat", "clusters_kerneldensity") > > # Compare > plot(mcmc1, "beta_num", "clusters_kerneldensity") > plot(mcmc2, "beta_num", "clusters_kerneldensity") > > > > > graphics::par(get("par.postscript", pos = 'CheckExEnv')) > cleanEx() > nameEx("predict.clustglmm") > ### * predict.clustglmm > > flush(stderr()); flush(stdout()) > > ### Name: predict.clustglmm > ### Title: Predict Method for Class 'clustglmm' > ### Aliases: predict.clustglmm > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### predict.clustglmm() > ###----------------------------------------------------------------------------- > > # By default, predicts the first outcome in mcmc$family > predict(mcmc, newdata = subset(longitudinal_mixed_type_data, i %in% 1:3), type = "link") $fit (2) (3) 1 -1.7406189 1.3164358 2 -1.4525809 1.0190803 3 -1.2331780 0.7925803 4 -0.5792473 0.1174964 5 -1.5482267 1.2124006 6 -1.0558069 0.7040522 7 -0.6210867 0.2552697 8 -0.5086943 0.1392417 9 -1.6028549 1.1742154 10 -1.5910125 1.1619899 11 -1.2726259 0.8333043 12 -0.6214847 0.1611000 $lwr (2) (3) 1 -2.1616357 0.95581330 2 -1.8549034 0.72532162 3 -1.6373003 0.53888662 4 -1.0112953 -0.30774399 5 -1.7745152 0.88731662 6 -1.2275564 0.50906014 7 -0.8497530 -0.06575386 8 -0.7547536 -0.23484341 9 -2.0039447 0.85301525 10 -1.9921994 0.84295229 11 -1.6764246 0.57240703 12 -1.0528425 -0.24794338 $upr (2) (3) 1 -1.29016854 1.6623410 2 -1.02086417 1.2934855 3 -0.77862735 1.0346656 4 -0.08619877 0.4482320 5 -1.18839366 1.5421178 6 -0.70805416 0.9999445 7 -0.24239709 0.6207452 8 -0.12200632 0.5354201 9 -1.16136454 1.4854213 10 -1.15029234 1.4702957 11 -0.82389668 1.0714265 12 -0.12696249 0.4829662 > # result is list of fit, lwr, upr matrices > > # Predict the evolution in time for covariate f=0 > newdata <- data.frame("x" = seq(0, 1, length.out=100), "f"=factor(0, levels=c(0,1))) > > ## Numeric outcome > # both fixed and group-specific part of the predictor > p1 <- predict(mcmc, newdata, y="ynum", type="link", what="fg") > # posterior predictive distribution of the response > p2 <- predict(mcmc, newdata, y="ynum", type="posterior_predictive_response") > > matplot(newdata$x, p1$fit, type = "l", lty = 1, lwd = 2) > matplot(newdata$x, p1$lwr, type = "l", lty = 2, add = TRUE) > matplot(newdata$x, p1$upr, type = "l", lty = 2, add = TRUE) > matplot(newdata$x, p2$lwr, type = "l", lty = 3, add = TRUE) # needs longer chains > matplot(newdata$x, p2$upr, type = "l", lty = 3, add = TRUE) # needs longer chains > > ## Count outcome - conditional mean > # predictor > pl <- predict(mcmc, newdata, y="ypoi", type="link") > # conditional mean > p1 <- predict(mcmc, newdata, y="ypoi", type="response") > # posterior predictive distribution > p2 <- predict(mcmc, newdata, y="ypoi", type="posterior_predictive_response") > > matplot(newdata$x, p1$fit, type = "l", lty = 1, lwd = 2) > matplot(newdata$x, p1$lwr, type = "l", lty = 2, add = TRUE) > matplot(newdata$x, p1$upr, type = "l", lty = 2, add = TRUE) > matplot(newdata$x, p2$lwr, type = "l", lty = 3, add = TRUE) # needs longer chains > matplot(newdata$x, p2$upr, type = "l", lty = 3, add = TRUE) # needs longer chains > > ## Categorical outcome - list of fit, lwr, upr 3D arrays (category dimension added) > predict(mcmc, newdata[1:5,], y="ycat", type="link", what="fg") $fit , , k=1 (2) (3) 1 0.9320677 -0.8267814 2 0.9281791 -0.8040474 3 0.9242905 -0.7813133 4 0.9204019 -0.7585792 5 0.9165132 -0.7358451 , , k=2 (2) (3) 1 -0.001053881 -0.3868644 2 0.014343563 -0.3877713 3 0.029741007 -0.3886783 4 0.045138451 -0.3895852 5 0.060535895 -0.3904922 , , k=3 (2) (3) 1 0.7735753 0.4169377 2 0.7807457 0.4179460 3 0.7879161 0.4189543 4 0.7950864 0.4199626 5 0.8022568 0.4209709 $lwr , , k=1 (2) (3) 1 -0.4673518 -2.321005 2 -0.4525743 -2.273194 3 -0.4377967 -2.225382 4 -0.4230192 -2.177570 5 -0.4082416 -2.129758 , , k=2 (2) (3) 1 -0.7854192 -1.771140 2 -0.7587237 -1.745952 3 -0.7320282 -1.720764 4 -0.7053326 -1.696137 5 -0.6786371 -1.675288 , , k=3 (2) (3) 1 0.3594423 -0.7629879 2 0.3691879 -0.7469666 3 0.3710211 -0.7309454 4 0.3724547 -0.7149241 5 0.3738884 -0.6989029 $upr , , k=1 (2) (3) 1 1.579768 -0.0194179264 2 1.566625 -0.0008470936 3 1.553483 0.0177237391 4 1.540341 0.0362945718 5 1.527199 0.0552294228 , , k=2 (2) (3) 1 0.9129704 0.8076706 2 0.9122462 0.7940684 3 0.9115220 0.7804662 4 0.9107978 0.7668639 5 0.9100736 0.7532617 , , k=3 (2) (3) 1 1.245455 1.471093 2 1.239176 1.462541 3 1.232898 1.453989 4 1.226619 1.445437 5 1.220341 1.437867 > > > > > cleanEx() > nameEx("print.clustglmm") > ### * print.clustglmm > > flush(stderr()); flush(stdout()) > > ### Name: print.clustglmm > ### Title: Print the Output of 'clustGLMM' > ### Aliases: print.clustglmm > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### Printing the results > ###----------------------------------------------------------------------------- > > mcmc ###------------------------------------------------------------### ### Model Based Clustering for Generalized Linear Mixed Models ### ###------------------------------------------------------------### N = sample size: 400 n = number of units: 100 observations per unit (min | median | max): 4 | 4 | 4 G = maximal number of components: 5 Overview of outcomes: num: ynum poi: ypoi bin: ybin ord: yord cat: ycat Fixed effects invariant towards clustering (in order of appearance): ynum ~ f ypoi ~ f ybin ~ f yord ~ f ycat ~ f Random effects invariant towards clustering: ynum ~ 1 ypoi ~ 1 ybin ~ 1 yord ~ 1 ycat ~ 1 The structure of covariance matrix Sigma for random effects: ynum_(Intercept) ypoi_(Intercept) ybin_(Intercept) yord_(Intercept) ycat_(Intercept) Group-specific effects for outcomes (in order of appearance): ynum ~ x ypoi ~ x ybin ~ x yord ~ x ycat ~ x Other group-specific parameters: prec_num, sd_num, var_num, c_ord, a_ord, pi_ord MCMC sampling: nchains = number of sampled chains: 2 iter = length of the chain: 100 Initialized by a random partition. > print(mcmc, which = "clustering") ## Clustering based on sampled indicators: ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- The most-frequent number of non-empty components: 2 Empty components: 1, 4, 5 Non-empty components: 2, 3 2 3 49 51 Average certainty of assignment to a component: 2 3 0.9814286 0.9600000 ----------------------------------------------------------------------- Chain 2 ----------------------------------------------------------------------- The most-frequent number of non-empty components: 3 Empty components: 2, 5 Non-empty components: 1, 3, 4 1 3 4 25 50 25 Average certainty of assignment to a component: 1 3 4 0.8252 0.9662 0.7676 > print(mcmc, which = c("call", "clustering")) ###------------------------------------------------------------### ### Model Based Clustering for Generalized Linear Mixed Models ### ###------------------------------------------------------------### N = sample size: 400 n = number of units: 100 observations per unit (min | median | max): 4 | 4 | 4 G = maximal number of components: 5 Overview of outcomes: num: ynum poi: ypoi bin: ybin ord: yord cat: ycat Fixed effects invariant towards clustering (in order of appearance): ynum ~ f ypoi ~ f ybin ~ f yord ~ f ycat ~ f Random effects invariant towards clustering: ynum ~ 1 ypoi ~ 1 ybin ~ 1 yord ~ 1 ycat ~ 1 The structure of covariance matrix Sigma for random effects: ynum_(Intercept) ypoi_(Intercept) ybin_(Intercept) yord_(Intercept) ycat_(Intercept) Group-specific effects for outcomes (in order of appearance): ynum ~ x ypoi ~ x ybin ~ x yord ~ x ycat ~ x Other group-specific parameters: prec_num, sd_num, var_num, c_ord, a_ord, pi_ord MCMC sampling: nchains = number of sampled chains: 2 iter = length of the chain: 100 Initialized by a random partition. ## Clustering based on sampled indicators: ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- The most-frequent number of non-empty components: 2 Empty components: 1, 4, 5 Non-empty components: 2, 3 2 3 49 51 Average certainty of assignment to a component: 2 3 0.9814286 0.9600000 ----------------------------------------------------------------------- Chain 2 ----------------------------------------------------------------------- The most-frequent number of non-empty components: 3 Empty components: 2, 5 Non-empty components: 1, 3, 4 1 3 4 25 50 25 Average certainty of assignment to a component: 1 3 4 0.8252 0.9662 0.7676 > > > > > cleanEx() > nameEx("psurvey") > ### * psurvey > > flush(stderr()); flush(stdout()) > > ### Name: psurvey > ### Title: A Simulated Panel Survey Data > ### Aliases: psurvey psurvey_latent > ### Keywords: datasets > > ### ** Examples > > data(psurvey) > head(psurvey) i j age income ntrips satisfaction 1 1 1 18.42013 95.01285 3 0 2 1 2 20.75503 103.02934 0 0 3 1 3 21.42530 108.03323 0 2 4 1 4 25.16883 127.68021 0 1 5 1 5 26.59334 152.50394 1 2 6 1 6 29.77266 160.85054 3 2 > summary(psurvey) i j age income Min. : 1.0 Min. : 1.000 Min. :18.00 Min. : 48.71 1st Qu.:125.8 1st Qu.: 3.000 1st Qu.:22.97 1st Qu.:112.32 Median :250.0 Median : 5.000 Median :28.95 Median :135.28 Mean :250.2 Mean : 5.072 Mean :29.01 Mean :134.36 3rd Qu.:375.2 3rd Qu.: 7.000 3rd Qu.:35.06 3rd Qu.:155.39 Max. :500.0 Max. :14.000 Max. :40.00 Max. :213.66 ntrips satisfaction Min. : 0.000 0:1340 1st Qu.: 1.000 1:1812 Median : 2.000 2:1360 Mean : 3.362 3rd Qu.: 4.000 Max. :37.000 > > data(psurvey_latent) > head(psurvey_latent) i j g b_num b_poi b_ord 1 1 1 3 3.083579 -0.3504447 0.1348468 2 1 2 3 3.083579 -0.3504447 0.1348468 3 1 3 3 3.083579 -0.3504447 0.1348468 4 1 4 3 3.083579 -0.3504447 0.1348468 5 1 5 3 3.083579 -0.3504447 0.1348468 6 1 6 3 3.083579 -0.3504447 0.1348468 > > > > cleanEx() > nameEx("rescale_matrix") > ### * rescale_matrix > > flush(stderr()); flush(stdout()) > > ### Name: rescale_matrix > ### Title: Rescale the Raw Draws > ### Aliases: rescale_matrix rescale_list > ### Keywords: internal > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains, + standardize = TRUE) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > # rescale_list or rescale_matrix have already been called inside clustGLMM!!! > > ###----------------------------------------------------------------------------- > ### !!! An illustrative use, does not make sense!!! > ### !!! output is already scaled back !!! > ###----------------------------------------------------------------------------- > some_draws <- vector("list", nchains) > for (ch in seq_len(nchains)) { + some_draws[[ch]] <- + rescale_matrix(mcmc$draws[[ch]], mcmc$settings[[ch]], + mcmc$family, mcmc$lfixnames, mcmc$lgrpnames, mcmc$lrannames, + mcmc$Kord, mcmc$Kcat, mcmc$centers, mcmc$scales) + } > > > > cleanEx() > nameEx("slategray.colors") > ### * slategray.colors > > flush(stderr()); flush(stdout()) > > ### Name: slategray.colors > ### Title: Slategray Color Palette > ### Aliases: slategray.colors slategrey.colors > > ### ** Examples > > slategray.colors(5, start = 0.3, end = 0.9) [1] "#98B0C6" "#A6C0D8" "#B1CDE7" "#BAD6F2" "#C0DDF9" > slategrey.colors(5, start = 0.1, end = 0.7) [1] "#7A8C9E" "#90A7BC" "#A2BBD3" "#ADC8E2" "#B8D4EF" > > > > cleanEx() > nameEx("summary.clustglmm") > ### * summary.clustglmm > > flush(stderr()); flush(stdout()) > > ### Name: summary.clustglmm > ### Title: Compute the Summary Statistics of 'clustGLMM' Output > ### Aliases: summary.clustglmm print.summary.clustglmm > > ### ** Examples > > > ### Get some longitudinal mixed type data > ### here generated by generate_longitudinal_mixed_type_data() > data("longitudinal_mixed_type_data") > > # Examples here demonstrate the basic use of the available functions on a toy dataset. > # For more thorough analyses see the vignettes. > > > ###----------------------------------------------------------------------------- > ### Prepare inputs for clustGLMM() > ###----------------------------------------------------------------------------- > id <- "i" > > family <- c("num", "poi", "bin", "ord", "cat") > names(family) <- Ys <- c("ynum", "ypoi", "ybin", "yord", "ycat") > > ## Create list of formulae for each outcome > formula <- list() > for(y in Ys){ + formula[[y]] <- list() + formula[[y]]$fixed <- ~ f + formula[[y]]$group <- ~ x + formula[[y]]$random <- ~ 1 + formula[[y]]$offset <- "" + } > formula $ynum $ynum$fixed ~f $ynum$group ~x $ynum$random ~1 $ynum$offset [1] "" $ypoi $ypoi$fixed ~f $ypoi$group ~x $ypoi$random ~1 $ypoi$offset [1] "" $ybin $ybin$fixed ~f $ybin$group ~x $ybin$random ~1 $ybin$offset [1] "" $yord $yord$fixed ~f $yord$group ~x $yord$random ~1 $yord$offset [1] "" $ycat $ycat$fixed ~f $ycat$group ~x $ycat$random ~1 $ycat$offset [1] "" > # intercept term will be group-specific > # since it appears in $group which has a preference over $fixed > > ## All other inputs need to be prepared, > ## unless the default values are desired (varying, save, howsave, param, tuning). > ## See the vignette for how these can be adjusted. > > ###----------------------------------------------------------------------------- > ### Calling clustGLMM() > ###----------------------------------------------------------------------------- > > Gmax <- 5 # maximal number of mixture components to be considered > nchains <- 2 # number of chains to be sampled > > ## No inits specified > set.seed(123456789) > mcmc <- clustGLMM(formula = formula, id = id, family = family, + data = longitudinal_mixed_type_data, + G = Gmax, iter = 100, nchains = nchains) Inits are missing, calculating... Inits are ready. Settings ready, about to start for ch in 1:nchains. Inits for chain 1 are ready. Triggering C function. Chain: 1, (1 %) Chain: 1, (2 %) Chain: 1, (3 %) Chain: 1, (4 %) Chain: 1, (5 %) Chain: 1, (6 %) Chain: 1, (7 %) Chain: 1, (8 %) Chain: 1, (9 %) Chain: 1, (10 %) Chain: 1, (11 %) Chain: 1, (12 %) Chain: 1, (13 %) Chain: 1, (14 %) Chain: 1, (15 %) Chain: 1, (16 %) Chain: 1, (17 %) Chain: 1, (18 %) Chain: 1, (19 %) Chain: 1, (20 %) Chain: 1, (21 %) Chain: 1, (22 %) Chain: 1, (23 %) Chain: 1, (24 %) Chain: 1, (25 %) Chain: 1, (26 %) Chain: 1, (27 %) Chain: 1, (28 %) Chain: 1, (29 %) Chain: 1, (30 %) Chain: 1, (31 %) Chain: 1, (32 %) Chain: 1, (33 %) Chain: 1, (34 %) Chain: 1, (35 %) Chain: 1, (36 %) Chain: 1, (37 %) Chain: 1, (38 %) Chain: 1, (39 %) Chain: 1, (40 %) Chain: 1, (41 %) Chain: 1, (42 %) Chain: 1, (43 %) Chain: 1, (44 %) Chain: 1, (45 %) Chain: 1, (46 %) Chain: 1, (47 %) Chain: 1, (48 %) Chain: 1, (49 %) Chain: 1, (50 %) Chain: 1, (51 %) Chain: 1, (52 %) Chain: 1, (53 %) Chain: 1, (54 %) Chain: 1, (55 %) Chain: 1, (56 %) Chain: 1, (57 %) Chain: 1, (58 %) Chain: 1, (59 %) Chain: 1, (60 %) Chain: 1, (61 %) Chain: 1, (62 %) Chain: 1, (63 %) Chain: 1, (64 %) Chain: 1, (65 %) Chain: 1, (66 %) Chain: 1, (67 %) Chain: 1, (68 %) Chain: 1, (69 %) Chain: 1, (70 %) Chain: 1, (71 %) Chain: 1, (72 %) Chain: 1, (73 %) Chain: 1, (74 %) Chain: 1, (75 %) Chain: 1, (76 %) Chain: 1, (77 %) Chain: 1, (78 %) Chain: 1, (79 %) Chain: 1, (80 %) Chain: 1, (81 %) Chain: 1, (82 %) Chain: 1, (83 %) Chain: 1, (84 %) Chain: 1, (85 %) Chain: 1, (86 %) Chain: 1, (87 %) Chain: 1, (88 %) Chain: 1, (89 %) Chain: 1, (90 %) Chain: 1, (91 %) Chain: 1, (92 %) Chain: 1, (93 %) Chain: 1, (94 %) Chain: 1, (95 %) Chain: 1, (96 %) Chain: 1, (97 %) Chain: 1, (98 %) Chain: 1, (99 %) Chain: 1, (100 %) Sampling of chain 1 is completed. Saving the last state of chain 1 is completed. Saving chain 1 is completed. Inits for chain 2 are ready. Triggering C function. Chain: 2, (1 %) Chain: 2, (2 %) Chain: 2, (3 %) Chain: 2, (4 %) Chain: 2, (5 %) Chain: 2, (6 %) Chain: 2, (7 %) Chain: 2, (8 %) Chain: 2, (9 %) Chain: 2, (10 %) Chain: 2, (11 %) Chain: 2, (12 %) Chain: 2, (13 %) Chain: 2, (14 %) Chain: 2, (15 %) Chain: 2, (16 %) Chain: 2, (17 %) Chain: 2, (18 %) Chain: 2, (19 %) Chain: 2, (20 %) Chain: 2, (21 %) Chain: 2, (22 %) Chain: 2, (23 %) Chain: 2, (24 %) Chain: 2, (25 %) Chain: 2, (26 %) Chain: 2, (27 %) Chain: 2, (28 %) Chain: 2, (29 %) Chain: 2, (30 %) Chain: 2, (31 %) Chain: 2, (32 %) Chain: 2, (33 %) Chain: 2, (34 %) Chain: 2, (35 %) Chain: 2, (36 %) Chain: 2, (37 %) Chain: 2, (38 %) Chain: 2, (39 %) Chain: 2, (40 %) Chain: 2, (41 %) Chain: 2, (42 %) Chain: 2, (43 %) Chain: 2, (44 %) Chain: 2, (45 %) Chain: 2, (46 %) Chain: 2, (47 %) Chain: 2, (48 %) Chain: 2, (49 %) Chain: 2, (50 %) Chain: 2, (51 %) Chain: 2, (52 %) Chain: 2, (53 %) Chain: 2, (54 %) Chain: 2, (55 %) Chain: 2, (56 %) Chain: 2, (57 %) Chain: 2, (58 %) Chain: 2, (59 %) Chain: 2, (60 %) Chain: 2, (61 %) Chain: 2, (62 %) Chain: 2, (63 %) Chain: 2, (64 %) Chain: 2, (65 %) Chain: 2, (66 %) Chain: 2, (67 %) Chain: 2, (68 %) Chain: 2, (69 %) Chain: 2, (70 %) Chain: 2, (71 %) Chain: 2, (72 %) Chain: 2, (73 %) Chain: 2, (74 %) Chain: 2, (75 %) Chain: 2, (76 %) Chain: 2, (77 %) Chain: 2, (78 %) Chain: 2, (79 %) Chain: 2, (80 %) Chain: 2, (81 %) Chain: 2, (82 %) Chain: 2, (83 %) Chain: 2, (84 %) Chain: 2, (85 %) Chain: 2, (86 %) Chain: 2, (87 %) Chain: 2, (88 %) Chain: 2, (89 %) Chain: 2, (90 %) Chain: 2, (91 %) Chain: 2, (92 %) Chain: 2, (93 %) Chain: 2, (94 %) Chain: 2, (95 %) Chain: 2, (96 %) Chain: 2, (97 %) Chain: 2, (98 %) Chain: 2, (99 %) Chain: 2, (100 %) Sampling of chain 2 is completed. Saving the last state of chain 2 is completed. Saving chain 2 is completed. All chains have been sampled. > > ###----------------------------------------------------------------------------- > ### summary.clustglmm() > ###----------------------------------------------------------------------------- > > mcmc ###------------------------------------------------------------### ### Model Based Clustering for Generalized Linear Mixed Models ### ###------------------------------------------------------------### N = sample size: 400 n = number of units: 100 observations per unit (min | median | max): 4 | 4 | 4 G = maximal number of components: 5 Overview of outcomes: num: ynum poi: ypoi bin: ybin ord: yord cat: ycat Fixed effects invariant towards clustering (in order of appearance): ynum ~ f ypoi ~ f ybin ~ f yord ~ f ycat ~ f Random effects invariant towards clustering: ynum ~ 1 ypoi ~ 1 ybin ~ 1 yord ~ 1 ycat ~ 1 The structure of covariance matrix Sigma for random effects: ynum_(Intercept) ypoi_(Intercept) ybin_(Intercept) yord_(Intercept) ycat_(Intercept) Group-specific effects for outcomes (in order of appearance): ynum ~ x ypoi ~ x ybin ~ x yord ~ x ycat ~ x Other group-specific parameters: prec_num, sd_num, var_num, c_ord, a_ord, pi_ord MCMC sampling: nchains = number of sampled chains: 2 iter = length of the chain: 100 Initialized by a random partition. > s <- summary(mcmc) > > # Choose chains - summary is done separately for each of them > print(s) ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Iterations = 1:100 Thinning interval = 1 Number of chains = 1 Sample size per chain = 100 Summary of the parameter estimates ----------------------------------------------------------------------- Cluster-invariant parameters: 2.5% 25% 50% Mean beta_num_fix_ynum[1] -0.22005389 -0.06012215 0.023634671 0.046537588 beta_poi_fix_ypoi[1] -0.23888674 -0.16726969 -0.113135751 -0.101814557 beta_bin_fix_ybin[1] -1.25366905 -0.96471886 -0.741922763 -0.725624744 beta_ord_fix_yord[1] 0.18380359 0.40619464 0.705118488 0.606841284 beta_cat_fix_ycat[1,1] -0.52028670 -0.27285322 -0.079933585 -0.078355970 beta_cat_fix_ycat[1,2] -0.44674883 -0.04474079 0.081720597 0.162318041 beta_cat_fix_ycat[1,3] -0.86384799 -0.54042971 -0.279715941 -0.311678216 InvSigma[1,1] 0.60748712 3.15912809 4.415377842 4.674695735 InvSigma[1,2] -0.33875499 0.45786010 2.598048297 2.467714235 InvSigma[2,2] 2.34135180 5.45182423 8.167226516 8.575751978 InvSigma[1,3] -0.64528370 -0.29547592 -0.159106929 -0.206336788 InvSigma[2,3] -0.97797177 -0.54632261 -0.166495723 -0.260845464 InvSigma[3,3] 0.09065762 0.19548538 0.293957912 0.316332492 InvSigma[1,4] -0.99612468 -0.55012886 -0.086335394 0.163543354 InvSigma[2,4] -2.33119912 -0.77294449 0.026885762 -0.197440116 InvSigma[3,4] -0.67988237 -0.34279131 -0.198798598 -0.242514989 InvSigma[4,4] 1.19337368 1.82004778 2.107877634 2.259916791 InvSigma[1,5] -0.74228715 -0.25665001 -0.031864693 -0.114948586 InvSigma[2,5] -1.28110138 -0.58444762 -0.314581524 -0.368466493 InvSigma[3,5] -0.12508157 -0.06489428 -0.040436486 -0.016998586 InvSigma[4,5] -0.41354194 -0.14573750 0.001432141 -0.034883024 InvSigma[5,5] 0.11377164 0.16991748 0.352774902 0.341225974 Sigma[1,1] 0.19974919 0.26210885 0.312266198 15.579466329 Sigma[1,2] -0.16962320 -0.11697361 -0.093612881 -0.907513412 Sigma[2,2] 0.11734973 0.15848805 0.189448566 6.018788087 Sigma[1,3] -0.26555275 -0.08566114 0.039828719 -0.279974843 Sigma[2,3] -0.49398083 -0.04141173 0.092064202 -1.090639721 Sigma[3,3] 2.35537863 3.28582839 4.404683800 12.516739742 Sigma[1,4] -0.21683154 -0.11426698 0.008637897 0.178965574 Sigma[2,4] -0.18979970 -0.05567451 0.025182578 0.185412880 Sigma[3,4] -0.22938135 0.32836185 0.458325655 1.161740798 Sigma[4,4] 0.42548280 0.51903283 0.627674457 5.954252981 Sigma[1,5] -0.45600562 -0.17175734 -0.062804412 -0.687591457 Sigma[2,5] -0.54235377 0.05361861 0.145489715 0.064829464 Sigma[3,5] -0.53461579 0.34862921 0.904936210 0.524622717 Sigma[4,5] -0.78688764 -0.16528962 0.049635321 0.009273198 Sigma[5,5] 1.89892891 2.66923414 3.592306082 10.767153084 sdSigma[1] 0.44693195 0.51196505 0.558806437 1.011318329 sdSigma[2] 0.34249697 0.39810556 0.435250327 0.701281288 sdSigma[3] 1.53472405 1.81268288 2.098728409 2.475623492 sdSigma[4] 0.65226380 0.72043891 0.792256874 1.024472341 sdSigma[5] 1.37798231 1.63376467 1.895337843 2.338762345 corSigma[1,2] -0.64443469 -0.53721512 -0.440114122 -0.348183015 corSigma[1,3] -0.27342710 -0.07521308 0.035576336 0.054229382 corSigma[2,3] -0.18406162 -0.03476902 0.113039567 0.136041150 corSigma[1,4] -0.53971327 -0.30903564 0.017815596 -0.015361196 corSigma[2,4] -0.37038561 -0.15375845 0.065916974 0.102362714 corSigma[3,4] -0.08197739 0.18109175 0.282116253 0.271550837 corSigma[1,5] -0.30697106 -0.14754419 -0.066597975 -0.051313272 corSigma[2,5] -0.21078329 0.05869181 0.228798310 0.187040084 corSigma[3,5] -0.15586053 0.09208582 0.224388451 0.198052726 corSigma[4,5] -0.30025376 -0.09873162 0.032409032 0.044146873 75% 97.5% beta_num_fix_ynum[1] 0.118354852 0.41333530 beta_poi_fix_ypoi[1] -0.050641354 0.05979616 beta_bin_fix_ybin[1] -0.514284972 -0.10050991 beta_ord_fix_yord[1] 0.705118488 0.95531074 beta_cat_fix_ycat[1,1] 0.100263621 0.35146686 beta_cat_fix_ycat[1,2] 0.343241132 0.72556674 beta_cat_fix_ycat[1,3] -0.168414199 0.17210946 InvSigma[1,1] 6.092434344 8.63337199 InvSigma[1,2] 3.983815180 6.38986946 InvSigma[2,2] 11.054653587 17.60555879 InvSigma[1,3] -0.062044244 0.03750619 InvSigma[2,3] 0.012987521 0.18611406 InvSigma[3,3] 0.421368119 0.62707120 InvSigma[1,4] 0.773270357 2.24726982 InvSigma[2,4] 0.410065450 1.08172179 InvSigma[3,4] -0.095857447 0.03066910 InvSigma[4,4] 2.581131733 3.90767010 InvSigma[1,5] 0.053532628 0.23981992 InvSigma[2,5] 0.002989948 0.21344687 InvSigma[3,5] 0.024448815 0.14397615 InvSigma[4,5] 0.087443017 0.19706314 InvSigma[5,5] 0.475961178 0.64405637 Sigma[1,1] 0.395251960 2.59519284 Sigma[1,2] -0.041767465 0.03422230 Sigma[2,2] 0.221389317 0.65897252 Sigma[1,3] 0.327897484 0.88217099 Sigma[2,3] 0.242592397 0.42748335 Sigma[3,3] 6.259134790 13.27060733 Sigma[1,4] 0.141823175 0.28290696 Sigma[2,4] 0.103963376 0.24174606 Sigma[3,4] 0.581645508 0.83355747 Sigma[4,4] 0.692600263 1.03338725 Sigma[1,5] 0.048713930 0.37861335 Sigma[2,5] 0.253297441 0.44996785 Sigma[3,5] 1.868990771 3.93281090 Sigma[4,5] 0.209960354 0.65668199 Sigma[5,5] 6.872436804 10.94791497 sdSigma[1] 0.628690430 1.54237499 sdSigma[2] 0.470517153 0.79161325 sdSigma[3] 2.501817915 3.64264065 sdSigma[4] 0.832225813 1.01630724 sdSigma[5] 2.621458320 3.30867197 corSigma[1,2] -0.148838335 0.10647087 corSigma[1,3] 0.200966661 0.36717339 corSigma[2,3] 0.313262242 0.50750531 corSigma[1,4] 0.264395871 0.46076043 corSigma[2,4] 0.364161626 0.59074756 corSigma[3,4] 0.378023226 0.53833734 corSigma[1,5] 0.043833947 0.25072209 corSigma[2,5] 0.330635116 0.47995005 corSigma[3,5] 0.328753913 0.46134077 corSigma[4,5] 0.188145708 0.37414071 Clustering-related parameters: 2.5% 25% 50% Mean 75% Gplus 2.000000e+00 2.000000e+00 2.000000e+00 2.350000000 2.250000e+00 e0 3.230175e-03 1.078316e-02 1.826189e-02 0.022687017 2.872600e-02 w(1) 3.476091e-80 5.978688e-30 3.454741e-17 0.004771686 1.212352e-07 w(2) 3.648725e-01 4.611620e-01 4.959707e-01 0.492190749 5.253257e-01 w(3) 2.816807e-01 4.667117e-01 4.943728e-01 0.485504036 5.296277e-01 w(4) 1.418373e-160 1.198650e-35 2.003603e-09 0.009792283 1.569152e-03 w(5) 1.699943e-129 2.519542e-37 1.692197e-17 0.007741245 6.357111e-08 97.5% Gplus 5.00000000 e0 0.06107483 w(1) 0.08672688 w(2) 0.57964697 w(3) 0.57637157 w(4) 0.08557175 w(5) 0.12253791 > print(s, chains = 2) ----------------------------------------------------------------------- Chain 2 ----------------------------------------------------------------------- Iterations = 1:100 Thinning interval = 1 Number of chains = 1 Sample size per chain = 100 Summary of the parameter estimates ----------------------------------------------------------------------- Cluster-invariant parameters: 2.5% 25% 50% Mean beta_num_fix_ynum[1] -0.27622357 -0.13631441 -0.0813898260 -0.062956443 beta_poi_fix_ypoi[1] -0.25565055 -0.15252495 -0.1012458778 -0.104377469 beta_bin_fix_ybin[1] -1.53922766 -1.14859534 -0.9045895298 -0.916968789 beta_ord_fix_yord[1] -0.16604359 0.21564825 0.5092490463 0.353586227 beta_cat_fix_ycat[1,1] -0.61635594 -0.29569441 -0.1063746220 -0.099198378 beta_cat_fix_ycat[1,2] -0.29425448 0.23883924 0.5202014187 0.451102077 beta_cat_fix_ycat[1,3] -1.17199848 -0.49572196 -0.0980964990 -0.114008015 InvSigma[1,1] 1.53861825 5.95037973 7.0280485744 7.159244879 InvSigma[1,2] 0.00375654 1.28555266 2.2910718136 2.389237944 InvSigma[2,2] 2.02913221 5.18630676 5.9961471763 5.960724900 InvSigma[1,3] -0.61829351 -0.10568918 0.0334752379 0.153948105 InvSigma[2,3] -0.26182946 -0.09204376 0.0599224230 0.078094318 InvSigma[3,3] 0.12984471 0.23366484 0.3990115934 0.495687787 InvSigma[1,4] -0.25868690 0.54366340 1.3020475525 1.365906729 InvSigma[2,4] -2.12192727 -1.31517830 -0.6590479283 -0.623754121 InvSigma[3,4] -0.63558347 -0.24259632 -0.1580286341 -0.179306525 InvSigma[4,4] 1.02699816 1.38487345 2.8059171008 2.751059855 InvSigma[1,5] -0.76106533 -0.20816413 -0.0474859088 -0.086867656 InvSigma[2,5] -0.99602171 -0.44025146 -0.2303811808 -0.249198783 InvSigma[3,5] -0.85816913 -0.30777951 -0.0124373620 -0.170212423 InvSigma[4,5] -0.18978264 0.02676416 0.1319767697 0.222471176 InvSigma[5,5] 0.08791332 0.19331683 0.3134318980 0.561193725 Sigma[1,1] 0.13819702 0.18716725 0.2223687280 10.478552238 Sigma[1,2] -0.17075552 -0.12172647 -0.0922741974 0.155924817 Sigma[2,2] 0.16791990 0.20959969 0.2376997334 6.467278254 Sigma[1,3] -0.34918455 -0.15526675 -0.0746673592 -0.096384390 Sigma[2,3] -0.28145056 -0.07524003 0.0354910196 0.153523623 Sigma[3,3] 1.06290585 2.13923942 2.8584582935 8.789922588 Sigma[1,4] -0.25278822 -0.16672818 -0.1216106272 -0.541284652 Sigma[2,4] -0.05583133 0.04353127 0.0993162545 0.451734678 Sigma[3,4] -0.17226402 0.09940058 0.2387127755 -0.408996473 Sigma[4,4] 0.29100601 0.40175514 0.5337536306 8.198714372 Sigma[1,5] -0.21668188 -0.05480797 -0.0006455231 0.840099415 Sigma[2,5] -0.65130313 -0.02510743 0.0642988711 0.372910648 Sigma[3,5] -1.76243401 -0.50576570 0.2771197731 0.812429839 Sigma[4,5] -0.97339037 -0.38329109 -0.1520573670 1.020648215 Sigma[5,5] 0.90661141 1.60359142 3.4742874375 10.690774295 sdSigma[1] 0.37173727 0.43262825 0.4715596508 0.841275459 sdSigma[2] 0.40975795 0.45781964 0.4875444128 0.771739563 sdSigma[3] 1.03096458 1.46257856 1.6906974702 2.055079279 sdSigma[4] 0.53943737 0.63384135 0.7305840545 1.063996497 sdSigma[5] 0.95205842 1.26632739 1.8638483024 2.190649513 corSigma[1,2] -0.66047512 -0.52461714 -0.4214552820 -0.413274858 corSigma[1,3] -0.43262551 -0.22319933 -0.0980158587 -0.089631794 corSigma[2,3] -0.21946910 -0.06635902 0.0374717530 0.027178793 corSigma[1,4] -0.62821906 -0.52515410 -0.3764725579 -0.332496072 corSigma[2,4] -0.12289761 0.08186505 0.3043011304 0.246449838 corSigma[3,4] -0.09891956 0.09017347 0.2031330504 0.186144404 corSigma[1,5] -0.24951043 -0.09628266 -0.0009289192 -0.001654795 corSigma[2,5] -0.36340606 -0.02481804 0.0798801730 0.058594138 corSigma[3,5] -0.26110508 -0.09916803 0.0951027505 0.127430969 corSigma[4,5] -0.36658775 -0.23071533 -0.1361024752 -0.124178155 75% 97.5% beta_num_fix_ynum[1] 0.021553566 0.16412044 beta_poi_fix_ypoi[1] -0.049195517 0.06818620 beta_bin_fix_ybin[1] -0.672504813 -0.43216688 beta_ord_fix_yord[1] 0.527885012 0.63427088 beta_cat_fix_ycat[1,1] 0.170793344 0.45343810 beta_cat_fix_ycat[1,2] 0.648408082 0.82104915 beta_cat_fix_ycat[1,3] 0.273733844 0.62733137 InvSigma[1,1] 8.476372122 12.63868549 InvSigma[1,2] 3.305523254 5.94800991 InvSigma[2,2] 6.957182006 8.86130406 InvSigma[1,3] 0.379251762 1.12504596 InvSigma[2,3] 0.204979664 0.54183411 InvSigma[3,3] 0.641272293 1.40963532 InvSigma[1,4] 2.033697622 3.61099411 InvSigma[2,4] 0.113777708 0.90017397 InvSigma[3,4] -0.057117355 0.22900094 InvSigma[4,4] 4.054607013 5.22159899 InvSigma[1,5] 0.067993387 0.37357146 InvSigma[2,5] 0.003448061 0.24011234 InvSigma[3,5] 0.023677083 0.05228445 InvSigma[4,5] 0.358675628 1.00254292 InvSigma[5,5] 0.824762713 1.74061002 Sigma[1,1] 0.251348207 1.24698280 Sigma[1,2] -0.069134402 0.07815929 Sigma[2,2] 0.263792885 0.96117084 Sigma[1,3] 0.048181906 0.30593839 Sigma[2,3] 0.088501237 0.21443250 Sigma[3,3] 5.018140456 8.40133542 Sigma[1,4] -0.068545606 0.05502081 Sigma[2,4] 0.139117937 0.43840174 Sigma[3,4] 0.478164755 0.77979764 Sigma[4,4] 0.855008959 1.38870248 Sigma[1,5] 0.075395483 0.50209744 Sigma[2,5] 0.133111678 0.30573816 Sigma[3,5] 0.662861650 1.42593738 Sigma[4,5] -0.021563887 0.23197174 Sigma[5,5] 5.965366944 12.54836186 sdSigma[1] 0.501346153 1.06090099 sdSigma[2] 0.513606248 0.93338166 sdSigma[3] 2.240114955 2.89812457 sdSigma[4] 0.924666912 1.17843199 sdSigma[5] 2.442359412 3.54222856 corSigma[1,2] -0.331869486 0.03819168 corSigma[1,3] 0.057331206 0.26582319 corSigma[2,3] 0.117525582 0.25753086 corSigma[1,4] -0.163944613 0.11754672 corSigma[2,4] 0.393374221 0.55793076 corSigma[3,4] 0.293018154 0.41112472 corSigma[1,5] 0.069960466 0.25214741 corSigma[2,5] 0.186086580 0.30622109 corSigma[3,5] 0.390691230 0.58326555 corSigma[4,5] -0.018783262 0.24045634 Clustering-related parameters: 2.5% 25% 50% Mean 75% Gplus 3.000000e+00 3.000000e+00 3.000000e+00 3.160000000 3.000000e+00 e0 8.329388e-03 2.206070e-02 3.143907e-02 0.032904681 4.288431e-02 w(1) 1.543913e-01 2.181975e-01 2.590946e-01 0.266527550 3.063743e-01 w(2) 8.080946e-78 8.167464e-23 2.002606e-10 0.013239094 1.133593e-05 w(3) 3.105809e-01 4.550922e-01 4.896958e-01 0.479542886 5.195606e-01 w(4) 1.153925e-01 1.930604e-01 2.333625e-01 0.233810978 2.782454e-01 w(5) 4.483798e-78 2.639679e-24 3.206643e-14 0.006879492 4.689068e-07 97.5% Gplus 5.00000000 e0 0.05853239 w(1) 0.39779814 w(2) 0.16472311 w(3) 0.58658871 w(4) 0.37605340 w(5) 0.11197447 > print(s, chains = c(1, 2)) ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Iterations = 1:100 Thinning interval = 1 Number of chains = 1 Sample size per chain = 100 Summary of the parameter estimates ----------------------------------------------------------------------- Cluster-invariant parameters: 2.5% 25% 50% Mean beta_num_fix_ynum[1] -0.22005389 -0.06012215 0.023634671 0.046537588 beta_poi_fix_ypoi[1] -0.23888674 -0.16726969 -0.113135751 -0.101814557 beta_bin_fix_ybin[1] -1.25366905 -0.96471886 -0.741922763 -0.725624744 beta_ord_fix_yord[1] 0.18380359 0.40619464 0.705118488 0.606841284 beta_cat_fix_ycat[1,1] -0.52028670 -0.27285322 -0.079933585 -0.078355970 beta_cat_fix_ycat[1,2] -0.44674883 -0.04474079 0.081720597 0.162318041 beta_cat_fix_ycat[1,3] -0.86384799 -0.54042971 -0.279715941 -0.311678216 InvSigma[1,1] 0.60748712 3.15912809 4.415377842 4.674695735 InvSigma[1,2] -0.33875499 0.45786010 2.598048297 2.467714235 InvSigma[2,2] 2.34135180 5.45182423 8.167226516 8.575751978 InvSigma[1,3] -0.64528370 -0.29547592 -0.159106929 -0.206336788 InvSigma[2,3] -0.97797177 -0.54632261 -0.166495723 -0.260845464 InvSigma[3,3] 0.09065762 0.19548538 0.293957912 0.316332492 InvSigma[1,4] -0.99612468 -0.55012886 -0.086335394 0.163543354 InvSigma[2,4] -2.33119912 -0.77294449 0.026885762 -0.197440116 InvSigma[3,4] -0.67988237 -0.34279131 -0.198798598 -0.242514989 InvSigma[4,4] 1.19337368 1.82004778 2.107877634 2.259916791 InvSigma[1,5] -0.74228715 -0.25665001 -0.031864693 -0.114948586 InvSigma[2,5] -1.28110138 -0.58444762 -0.314581524 -0.368466493 InvSigma[3,5] -0.12508157 -0.06489428 -0.040436486 -0.016998586 InvSigma[4,5] -0.41354194 -0.14573750 0.001432141 -0.034883024 InvSigma[5,5] 0.11377164 0.16991748 0.352774902 0.341225974 Sigma[1,1] 0.19974919 0.26210885 0.312266198 15.579466329 Sigma[1,2] -0.16962320 -0.11697361 -0.093612881 -0.907513412 Sigma[2,2] 0.11734973 0.15848805 0.189448566 6.018788087 Sigma[1,3] -0.26555275 -0.08566114 0.039828719 -0.279974843 Sigma[2,3] -0.49398083 -0.04141173 0.092064202 -1.090639721 Sigma[3,3] 2.35537863 3.28582839 4.404683800 12.516739742 Sigma[1,4] -0.21683154 -0.11426698 0.008637897 0.178965574 Sigma[2,4] -0.18979970 -0.05567451 0.025182578 0.185412880 Sigma[3,4] -0.22938135 0.32836185 0.458325655 1.161740798 Sigma[4,4] 0.42548280 0.51903283 0.627674457 5.954252981 Sigma[1,5] -0.45600562 -0.17175734 -0.062804412 -0.687591457 Sigma[2,5] -0.54235377 0.05361861 0.145489715 0.064829464 Sigma[3,5] -0.53461579 0.34862921 0.904936210 0.524622717 Sigma[4,5] -0.78688764 -0.16528962 0.049635321 0.009273198 Sigma[5,5] 1.89892891 2.66923414 3.592306082 10.767153084 sdSigma[1] 0.44693195 0.51196505 0.558806437 1.011318329 sdSigma[2] 0.34249697 0.39810556 0.435250327 0.701281288 sdSigma[3] 1.53472405 1.81268288 2.098728409 2.475623492 sdSigma[4] 0.65226380 0.72043891 0.792256874 1.024472341 sdSigma[5] 1.37798231 1.63376467 1.895337843 2.338762345 corSigma[1,2] -0.64443469 -0.53721512 -0.440114122 -0.348183015 corSigma[1,3] -0.27342710 -0.07521308 0.035576336 0.054229382 corSigma[2,3] -0.18406162 -0.03476902 0.113039567 0.136041150 corSigma[1,4] -0.53971327 -0.30903564 0.017815596 -0.015361196 corSigma[2,4] -0.37038561 -0.15375845 0.065916974 0.102362714 corSigma[3,4] -0.08197739 0.18109175 0.282116253 0.271550837 corSigma[1,5] -0.30697106 -0.14754419 -0.066597975 -0.051313272 corSigma[2,5] -0.21078329 0.05869181 0.228798310 0.187040084 corSigma[3,5] -0.15586053 0.09208582 0.224388451 0.198052726 corSigma[4,5] -0.30025376 -0.09873162 0.032409032 0.044146873 75% 97.5% beta_num_fix_ynum[1] 0.118354852 0.41333530 beta_poi_fix_ypoi[1] -0.050641354 0.05979616 beta_bin_fix_ybin[1] -0.514284972 -0.10050991 beta_ord_fix_yord[1] 0.705118488 0.95531074 beta_cat_fix_ycat[1,1] 0.100263621 0.35146686 beta_cat_fix_ycat[1,2] 0.343241132 0.72556674 beta_cat_fix_ycat[1,3] -0.168414199 0.17210946 InvSigma[1,1] 6.092434344 8.63337199 InvSigma[1,2] 3.983815180 6.38986946 InvSigma[2,2] 11.054653587 17.60555879 InvSigma[1,3] -0.062044244 0.03750619 InvSigma[2,3] 0.012987521 0.18611406 InvSigma[3,3] 0.421368119 0.62707120 InvSigma[1,4] 0.773270357 2.24726982 InvSigma[2,4] 0.410065450 1.08172179 InvSigma[3,4] -0.095857447 0.03066910 InvSigma[4,4] 2.581131733 3.90767010 InvSigma[1,5] 0.053532628 0.23981992 InvSigma[2,5] 0.002989948 0.21344687 InvSigma[3,5] 0.024448815 0.14397615 InvSigma[4,5] 0.087443017 0.19706314 InvSigma[5,5] 0.475961178 0.64405637 Sigma[1,1] 0.395251960 2.59519284 Sigma[1,2] -0.041767465 0.03422230 Sigma[2,2] 0.221389317 0.65897252 Sigma[1,3] 0.327897484 0.88217099 Sigma[2,3] 0.242592397 0.42748335 Sigma[3,3] 6.259134790 13.27060733 Sigma[1,4] 0.141823175 0.28290696 Sigma[2,4] 0.103963376 0.24174606 Sigma[3,4] 0.581645508 0.83355747 Sigma[4,4] 0.692600263 1.03338725 Sigma[1,5] 0.048713930 0.37861335 Sigma[2,5] 0.253297441 0.44996785 Sigma[3,5] 1.868990771 3.93281090 Sigma[4,5] 0.209960354 0.65668199 Sigma[5,5] 6.872436804 10.94791497 sdSigma[1] 0.628690430 1.54237499 sdSigma[2] 0.470517153 0.79161325 sdSigma[3] 2.501817915 3.64264065 sdSigma[4] 0.832225813 1.01630724 sdSigma[5] 2.621458320 3.30867197 corSigma[1,2] -0.148838335 0.10647087 corSigma[1,3] 0.200966661 0.36717339 corSigma[2,3] 0.313262242 0.50750531 corSigma[1,4] 0.264395871 0.46076043 corSigma[2,4] 0.364161626 0.59074756 corSigma[3,4] 0.378023226 0.53833734 corSigma[1,5] 0.043833947 0.25072209 corSigma[2,5] 0.330635116 0.47995005 corSigma[3,5] 0.328753913 0.46134077 corSigma[4,5] 0.188145708 0.37414071 Clustering-related parameters: 2.5% 25% 50% Mean 75% Gplus 2.000000e+00 2.000000e+00 2.000000e+00 2.350000000 2.250000e+00 e0 3.230175e-03 1.078316e-02 1.826189e-02 0.022687017 2.872600e-02 w(1) 3.476091e-80 5.978688e-30 3.454741e-17 0.004771686 1.212352e-07 w(2) 3.648725e-01 4.611620e-01 4.959707e-01 0.492190749 5.253257e-01 w(3) 2.816807e-01 4.667117e-01 4.943728e-01 0.485504036 5.296277e-01 w(4) 1.418373e-160 1.198650e-35 2.003603e-09 0.009792283 1.569152e-03 w(5) 1.699943e-129 2.519542e-37 1.692197e-17 0.007741245 6.357111e-08 97.5% Gplus 5.00000000 e0 0.06107483 w(1) 0.08672688 w(2) 0.57964697 w(3) 0.57637157 w(4) 0.08557175 w(5) 0.12253791 ----------------------------------------------------------------------- Chain 2 ----------------------------------------------------------------------- Iterations = 1:100 Thinning interval = 1 Number of chains = 1 Sample size per chain = 100 Summary of the parameter estimates ----------------------------------------------------------------------- Cluster-invariant parameters: 2.5% 25% 50% Mean beta_num_fix_ynum[1] -0.27622357 -0.13631441 -0.0813898260 -0.062956443 beta_poi_fix_ypoi[1] -0.25565055 -0.15252495 -0.1012458778 -0.104377469 beta_bin_fix_ybin[1] -1.53922766 -1.14859534 -0.9045895298 -0.916968789 beta_ord_fix_yord[1] -0.16604359 0.21564825 0.5092490463 0.353586227 beta_cat_fix_ycat[1,1] -0.61635594 -0.29569441 -0.1063746220 -0.099198378 beta_cat_fix_ycat[1,2] -0.29425448 0.23883924 0.5202014187 0.451102077 beta_cat_fix_ycat[1,3] -1.17199848 -0.49572196 -0.0980964990 -0.114008015 InvSigma[1,1] 1.53861825 5.95037973 7.0280485744 7.159244879 InvSigma[1,2] 0.00375654 1.28555266 2.2910718136 2.389237944 InvSigma[2,2] 2.02913221 5.18630676 5.9961471763 5.960724900 InvSigma[1,3] -0.61829351 -0.10568918 0.0334752379 0.153948105 InvSigma[2,3] -0.26182946 -0.09204376 0.0599224230 0.078094318 InvSigma[3,3] 0.12984471 0.23366484 0.3990115934 0.495687787 InvSigma[1,4] -0.25868690 0.54366340 1.3020475525 1.365906729 InvSigma[2,4] -2.12192727 -1.31517830 -0.6590479283 -0.623754121 InvSigma[3,4] -0.63558347 -0.24259632 -0.1580286341 -0.179306525 InvSigma[4,4] 1.02699816 1.38487345 2.8059171008 2.751059855 InvSigma[1,5] -0.76106533 -0.20816413 -0.0474859088 -0.086867656 InvSigma[2,5] -0.99602171 -0.44025146 -0.2303811808 -0.249198783 InvSigma[3,5] -0.85816913 -0.30777951 -0.0124373620 -0.170212423 InvSigma[4,5] -0.18978264 0.02676416 0.1319767697 0.222471176 InvSigma[5,5] 0.08791332 0.19331683 0.3134318980 0.561193725 Sigma[1,1] 0.13819702 0.18716725 0.2223687280 10.478552238 Sigma[1,2] -0.17075552 -0.12172647 -0.0922741974 0.155924817 Sigma[2,2] 0.16791990 0.20959969 0.2376997334 6.467278254 Sigma[1,3] -0.34918455 -0.15526675 -0.0746673592 -0.096384390 Sigma[2,3] -0.28145056 -0.07524003 0.0354910196 0.153523623 Sigma[3,3] 1.06290585 2.13923942 2.8584582935 8.789922588 Sigma[1,4] -0.25278822 -0.16672818 -0.1216106272 -0.541284652 Sigma[2,4] -0.05583133 0.04353127 0.0993162545 0.451734678 Sigma[3,4] -0.17226402 0.09940058 0.2387127755 -0.408996473 Sigma[4,4] 0.29100601 0.40175514 0.5337536306 8.198714372 Sigma[1,5] -0.21668188 -0.05480797 -0.0006455231 0.840099415 Sigma[2,5] -0.65130313 -0.02510743 0.0642988711 0.372910648 Sigma[3,5] -1.76243401 -0.50576570 0.2771197731 0.812429839 Sigma[4,5] -0.97339037 -0.38329109 -0.1520573670 1.020648215 Sigma[5,5] 0.90661141 1.60359142 3.4742874375 10.690774295 sdSigma[1] 0.37173727 0.43262825 0.4715596508 0.841275459 sdSigma[2] 0.40975795 0.45781964 0.4875444128 0.771739563 sdSigma[3] 1.03096458 1.46257856 1.6906974702 2.055079279 sdSigma[4] 0.53943737 0.63384135 0.7305840545 1.063996497 sdSigma[5] 0.95205842 1.26632739 1.8638483024 2.190649513 corSigma[1,2] -0.66047512 -0.52461714 -0.4214552820 -0.413274858 corSigma[1,3] -0.43262551 -0.22319933 -0.0980158587 -0.089631794 corSigma[2,3] -0.21946910 -0.06635902 0.0374717530 0.027178793 corSigma[1,4] -0.62821906 -0.52515410 -0.3764725579 -0.332496072 corSigma[2,4] -0.12289761 0.08186505 0.3043011304 0.246449838 corSigma[3,4] -0.09891956 0.09017347 0.2031330504 0.186144404 corSigma[1,5] -0.24951043 -0.09628266 -0.0009289192 -0.001654795 corSigma[2,5] -0.36340606 -0.02481804 0.0798801730 0.058594138 corSigma[3,5] -0.26110508 -0.09916803 0.0951027505 0.127430969 corSigma[4,5] -0.36658775 -0.23071533 -0.1361024752 -0.124178155 75% 97.5% beta_num_fix_ynum[1] 0.021553566 0.16412044 beta_poi_fix_ypoi[1] -0.049195517 0.06818620 beta_bin_fix_ybin[1] -0.672504813 -0.43216688 beta_ord_fix_yord[1] 0.527885012 0.63427088 beta_cat_fix_ycat[1,1] 0.170793344 0.45343810 beta_cat_fix_ycat[1,2] 0.648408082 0.82104915 beta_cat_fix_ycat[1,3] 0.273733844 0.62733137 InvSigma[1,1] 8.476372122 12.63868549 InvSigma[1,2] 3.305523254 5.94800991 InvSigma[2,2] 6.957182006 8.86130406 InvSigma[1,3] 0.379251762 1.12504596 InvSigma[2,3] 0.204979664 0.54183411 InvSigma[3,3] 0.641272293 1.40963532 InvSigma[1,4] 2.033697622 3.61099411 InvSigma[2,4] 0.113777708 0.90017397 InvSigma[3,4] -0.057117355 0.22900094 InvSigma[4,4] 4.054607013 5.22159899 InvSigma[1,5] 0.067993387 0.37357146 InvSigma[2,5] 0.003448061 0.24011234 InvSigma[3,5] 0.023677083 0.05228445 InvSigma[4,5] 0.358675628 1.00254292 InvSigma[5,5] 0.824762713 1.74061002 Sigma[1,1] 0.251348207 1.24698280 Sigma[1,2] -0.069134402 0.07815929 Sigma[2,2] 0.263792885 0.96117084 Sigma[1,3] 0.048181906 0.30593839 Sigma[2,3] 0.088501237 0.21443250 Sigma[3,3] 5.018140456 8.40133542 Sigma[1,4] -0.068545606 0.05502081 Sigma[2,4] 0.139117937 0.43840174 Sigma[3,4] 0.478164755 0.77979764 Sigma[4,4] 0.855008959 1.38870248 Sigma[1,5] 0.075395483 0.50209744 Sigma[2,5] 0.133111678 0.30573816 Sigma[3,5] 0.662861650 1.42593738 Sigma[4,5] -0.021563887 0.23197174 Sigma[5,5] 5.965366944 12.54836186 sdSigma[1] 0.501346153 1.06090099 sdSigma[2] 0.513606248 0.93338166 sdSigma[3] 2.240114955 2.89812457 sdSigma[4] 0.924666912 1.17843199 sdSigma[5] 2.442359412 3.54222856 corSigma[1,2] -0.331869486 0.03819168 corSigma[1,3] 0.057331206 0.26582319 corSigma[2,3] 0.117525582 0.25753086 corSigma[1,4] -0.163944613 0.11754672 corSigma[2,4] 0.393374221 0.55793076 corSigma[3,4] 0.293018154 0.41112472 corSigma[1,5] 0.069960466 0.25214741 corSigma[2,5] 0.186086580 0.30622109 corSigma[3,5] 0.390691230 0.58326555 corSigma[4,5] -0.018783262 0.24045634 Clustering-related parameters: 2.5% 25% 50% Mean 75% Gplus 3.000000e+00 3.000000e+00 3.000000e+00 3.160000000 3.000000e+00 e0 8.329388e-03 2.206070e-02 3.143907e-02 0.032904681 4.288431e-02 w(1) 1.543913e-01 2.181975e-01 2.590946e-01 0.266527550 3.063743e-01 w(2) 8.080946e-78 8.167464e-23 2.002606e-10 0.013239094 1.133593e-05 w(3) 3.105809e-01 4.550922e-01 4.896958e-01 0.479542886 5.195606e-01 w(4) 1.153925e-01 1.930604e-01 2.333625e-01 0.233810978 2.782454e-01 w(5) 4.483798e-78 2.639679e-24 3.206643e-14 0.006879492 4.689068e-07 97.5% Gplus 5.00000000 e0 0.05853239 w(1) 0.39779814 w(2) 0.16472311 w(3) 0.58658871 w(4) 0.37605340 w(5) 0.11197447 > > # Different types of summary > print(s, which = c("mcmc", "clustering")) ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Iterations = 1:100 Thinning interval = 1 Number of chains = 1 Sample size per chain = 100 Summary of the clustering based on sampled allocation indicators U ----------------------------------------------------------------------- The most-frequent number of non-empty components: 2 Empty components: 1, 4, 5 Non-empty components: 2, 3 2 3 49 51 Average certainty of clustering into a cluster: 2 3 0.9814286 0.9600000 > print(s, which = "inv_param") ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Summary of the parameter estimates ----------------------------------------------------------------------- Cluster-invariant parameters: 2.5% 25% 50% Mean beta_num_fix_ynum[1] -0.22005389 -0.06012215 0.023634671 0.046537588 beta_poi_fix_ypoi[1] -0.23888674 -0.16726969 -0.113135751 -0.101814557 beta_bin_fix_ybin[1] -1.25366905 -0.96471886 -0.741922763 -0.725624744 beta_ord_fix_yord[1] 0.18380359 0.40619464 0.705118488 0.606841284 beta_cat_fix_ycat[1,1] -0.52028670 -0.27285322 -0.079933585 -0.078355970 beta_cat_fix_ycat[1,2] -0.44674883 -0.04474079 0.081720597 0.162318041 beta_cat_fix_ycat[1,3] -0.86384799 -0.54042971 -0.279715941 -0.311678216 InvSigma[1,1] 0.60748712 3.15912809 4.415377842 4.674695735 InvSigma[1,2] -0.33875499 0.45786010 2.598048297 2.467714235 InvSigma[2,2] 2.34135180 5.45182423 8.167226516 8.575751978 InvSigma[1,3] -0.64528370 -0.29547592 -0.159106929 -0.206336788 InvSigma[2,3] -0.97797177 -0.54632261 -0.166495723 -0.260845464 InvSigma[3,3] 0.09065762 0.19548538 0.293957912 0.316332492 InvSigma[1,4] -0.99612468 -0.55012886 -0.086335394 0.163543354 InvSigma[2,4] -2.33119912 -0.77294449 0.026885762 -0.197440116 InvSigma[3,4] -0.67988237 -0.34279131 -0.198798598 -0.242514989 InvSigma[4,4] 1.19337368 1.82004778 2.107877634 2.259916791 InvSigma[1,5] -0.74228715 -0.25665001 -0.031864693 -0.114948586 InvSigma[2,5] -1.28110138 -0.58444762 -0.314581524 -0.368466493 InvSigma[3,5] -0.12508157 -0.06489428 -0.040436486 -0.016998586 InvSigma[4,5] -0.41354194 -0.14573750 0.001432141 -0.034883024 InvSigma[5,5] 0.11377164 0.16991748 0.352774902 0.341225974 Sigma[1,1] 0.19974919 0.26210885 0.312266198 15.579466329 Sigma[1,2] -0.16962320 -0.11697361 -0.093612881 -0.907513412 Sigma[2,2] 0.11734973 0.15848805 0.189448566 6.018788087 Sigma[1,3] -0.26555275 -0.08566114 0.039828719 -0.279974843 Sigma[2,3] -0.49398083 -0.04141173 0.092064202 -1.090639721 Sigma[3,3] 2.35537863 3.28582839 4.404683800 12.516739742 Sigma[1,4] -0.21683154 -0.11426698 0.008637897 0.178965574 Sigma[2,4] -0.18979970 -0.05567451 0.025182578 0.185412880 Sigma[3,4] -0.22938135 0.32836185 0.458325655 1.161740798 Sigma[4,4] 0.42548280 0.51903283 0.627674457 5.954252981 Sigma[1,5] -0.45600562 -0.17175734 -0.062804412 -0.687591457 Sigma[2,5] -0.54235377 0.05361861 0.145489715 0.064829464 Sigma[3,5] -0.53461579 0.34862921 0.904936210 0.524622717 Sigma[4,5] -0.78688764 -0.16528962 0.049635321 0.009273198 Sigma[5,5] 1.89892891 2.66923414 3.592306082 10.767153084 sdSigma[1] 0.44693195 0.51196505 0.558806437 1.011318329 sdSigma[2] 0.34249697 0.39810556 0.435250327 0.701281288 sdSigma[3] 1.53472405 1.81268288 2.098728409 2.475623492 sdSigma[4] 0.65226380 0.72043891 0.792256874 1.024472341 sdSigma[5] 1.37798231 1.63376467 1.895337843 2.338762345 corSigma[1,2] -0.64443469 -0.53721512 -0.440114122 -0.348183015 corSigma[1,3] -0.27342710 -0.07521308 0.035576336 0.054229382 corSigma[2,3] -0.18406162 -0.03476902 0.113039567 0.136041150 corSigma[1,4] -0.53971327 -0.30903564 0.017815596 -0.015361196 corSigma[2,4] -0.37038561 -0.15375845 0.065916974 0.102362714 corSigma[3,4] -0.08197739 0.18109175 0.282116253 0.271550837 corSigma[1,5] -0.30697106 -0.14754419 -0.066597975 -0.051313272 corSigma[2,5] -0.21078329 0.05869181 0.228798310 0.187040084 corSigma[3,5] -0.15586053 0.09208582 0.224388451 0.198052726 corSigma[4,5] -0.30025376 -0.09873162 0.032409032 0.044146873 75% 97.5% beta_num_fix_ynum[1] 0.118354852 0.41333530 beta_poi_fix_ypoi[1] -0.050641354 0.05979616 beta_bin_fix_ybin[1] -0.514284972 -0.10050991 beta_ord_fix_yord[1] 0.705118488 0.95531074 beta_cat_fix_ycat[1,1] 0.100263621 0.35146686 beta_cat_fix_ycat[1,2] 0.343241132 0.72556674 beta_cat_fix_ycat[1,3] -0.168414199 0.17210946 InvSigma[1,1] 6.092434344 8.63337199 InvSigma[1,2] 3.983815180 6.38986946 InvSigma[2,2] 11.054653587 17.60555879 InvSigma[1,3] -0.062044244 0.03750619 InvSigma[2,3] 0.012987521 0.18611406 InvSigma[3,3] 0.421368119 0.62707120 InvSigma[1,4] 0.773270357 2.24726982 InvSigma[2,4] 0.410065450 1.08172179 InvSigma[3,4] -0.095857447 0.03066910 InvSigma[4,4] 2.581131733 3.90767010 InvSigma[1,5] 0.053532628 0.23981992 InvSigma[2,5] 0.002989948 0.21344687 InvSigma[3,5] 0.024448815 0.14397615 InvSigma[4,5] 0.087443017 0.19706314 InvSigma[5,5] 0.475961178 0.64405637 Sigma[1,1] 0.395251960 2.59519284 Sigma[1,2] -0.041767465 0.03422230 Sigma[2,2] 0.221389317 0.65897252 Sigma[1,3] 0.327897484 0.88217099 Sigma[2,3] 0.242592397 0.42748335 Sigma[3,3] 6.259134790 13.27060733 Sigma[1,4] 0.141823175 0.28290696 Sigma[2,4] 0.103963376 0.24174606 Sigma[3,4] 0.581645508 0.83355747 Sigma[4,4] 0.692600263 1.03338725 Sigma[1,5] 0.048713930 0.37861335 Sigma[2,5] 0.253297441 0.44996785 Sigma[3,5] 1.868990771 3.93281090 Sigma[4,5] 0.209960354 0.65668199 Sigma[5,5] 6.872436804 10.94791497 sdSigma[1] 0.628690430 1.54237499 sdSigma[2] 0.470517153 0.79161325 sdSigma[3] 2.501817915 3.64264065 sdSigma[4] 0.832225813 1.01630724 sdSigma[5] 2.621458320 3.30867197 corSigma[1,2] -0.148838335 0.10647087 corSigma[1,3] 0.200966661 0.36717339 corSigma[2,3] 0.313262242 0.50750531 corSigma[1,4] 0.264395871 0.46076043 corSigma[2,4] 0.364161626 0.59074756 corSigma[3,4] 0.378023226 0.53833734 corSigma[1,5] 0.043833947 0.25072209 corSigma[2,5] 0.330635116 0.47995005 corSigma[3,5] 0.328753913 0.46134077 corSigma[4,5] 0.188145708 0.37414071 > print(s, which = "clust_param") ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Summary of the parameter estimates ----------------------------------------------------------------------- Clustering-related parameters: 2.5% 25% 50% Mean 75% Gplus 2.000000e+00 2.000000e+00 2.000000e+00 2.350000000 2.250000e+00 e0 3.230175e-03 1.078316e-02 1.826189e-02 0.022687017 2.872600e-02 w(1) 3.476091e-80 5.978688e-30 3.454741e-17 0.004771686 1.212352e-07 w(2) 3.648725e-01 4.611620e-01 4.959707e-01 0.492190749 5.253257e-01 w(3) 2.816807e-01 4.667117e-01 4.943728e-01 0.485504036 5.296277e-01 w(4) 1.418373e-160 1.198650e-35 2.003603e-09 0.009792283 1.569152e-03 w(5) 1.699943e-129 2.519542e-37 1.692197e-17 0.007741245 6.357111e-08 97.5% Gplus 5.00000000 e0 0.06107483 w(1) 0.08672688 w(2) 0.57964697 w(3) 0.57637157 w(4) 0.08557175 w(5) 0.12253791 > print(s, which = "latent_param") ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Summary of the parameter estimates ----------------------------------------------------------------------- Latent variables: 2.5% 25% 50% Mean 75% 97.5% U[1] 3.00 3 3 3.00 3.0 3.000 U[2] 3.00 3 3 3.08 3.0 5.000 U[3] 2.00 2 2 2.00 2.0 2.000 U[4] 2.00 2 2 2.09 2.0 3.575 U[5] 2.00 2 2 2.00 2.0 2.000 U[6] 1.95 3 3 2.94 3.0 3.000 U[7] 3.00 3 3 3.02 3.0 3.000 U[8] 2.00 2 2 2.03 2.0 2.000 U[9] 2.00 2 2 2.04 2.0 2.000 U[10] 2.00 3 3 2.86 3.0 3.000 U[11] 2.00 3 3 2.97 3.0 3.000 U[12] 2.00 2 2 2.00 2.0 2.000 U[13] 3.00 3 3 3.04 3.0 3.000 U[14] 1.95 3 3 2.94 3.0 3.000 U[15] 2.00 2 2 2.02 2.0 2.000 U[16] 3.00 3 3 3.00 3.0 3.000 U[17] 3.00 3 3 2.99 3.0 3.000 U[18] 2.00 2 2 2.00 2.0 2.000 U[19] 3.00 3 3 3.02 3.0 3.000 U[20] 2.00 2 2 2.05 2.0 2.000 U[21] 2.00 2 3 2.71 3.0 5.000 U[22] 2.00 2 2 2.08 2.0 4.000 U[23] 3.00 3 3 2.96 3.0 3.000 U[24] 2.00 2 2 2.03 2.0 2.000 U[25] 3.00 3 3 2.98 3.0 3.000 U[26] 2.00 2 2 2.03 2.0 2.000 U[27] 2.00 2 2 1.99 2.0 2.000 U[28] 2.00 2 2 2.02 2.0 2.000 U[29] 2.00 2 3 2.71 3.0 3.000 U[30] 3.00 3 3 3.00 3.0 3.000 U[31] 2.00 2 2 1.99 2.0 2.000 U[32] 3.00 3 3 3.00 3.0 3.000 U[33] 3.00 3 3 3.04 3.0 3.000 U[34] 3.00 3 3 3.03 3.0 3.000 U[35] 3.00 3 3 2.99 3.0 3.000 U[36] 3.00 3 3 2.98 3.0 3.000 U[37] 3.00 3 3 3.02 3.0 3.000 U[38] 3.00 3 3 2.98 3.0 3.000 U[39] 2.00 2 2 2.00 2.0 2.000 U[40] 3.00 3 3 3.03 3.0 3.000 U[41] 2.00 2 2 1.99 2.0 2.000 U[42] 3.00 3 3 3.08 3.0 4.525 U[43] 3.00 3 3 3.00 3.0 3.000 U[44] 2.00 2 2 2.06 2.0 3.050 U[45] 2.00 2 2 2.03 2.0 2.000 U[46] 3.00 3 3 2.99 3.0 3.000 U[47] 2.00 2 2 2.12 2.0 4.000 U[48] 2.00 2 2 2.01 2.0 2.000 U[49] 2.00 2 2 2.02 2.0 2.000 U[50] 3.00 3 3 3.00 3.0 3.000 U[51] 3.00 3 3 3.06 3.0 4.050 U[52] 3.00 3 3 3.01 3.0 3.000 U[53] 2.00 2 2 2.00 2.0 2.000 U[54] 3.00 3 3 3.00 3.0 3.000 U[55] 2.00 2 2 2.00 2.0 2.000 U[56] 3.00 3 3 3.04 3.0 3.000 U[57] 2.00 2 2 2.00 2.0 2.000 U[58] 2.00 2 2 2.03 2.0 2.000 U[59] 2.00 2 2 1.99 2.0 2.000 U[60] 2.00 2 2 2.00 2.0 2.000 U[61] 3.00 3 3 3.00 3.0 3.000 U[62] 3.00 3 3 3.02 3.0 3.000 U[63] 2.00 2 2 2.00 2.0 2.000 U[64] 2.00 2 2 2.00 2.0 2.000 U[65] 2.00 2 2 1.99 2.0 2.000 U[66] 2.00 2 2 2.00 2.0 2.000 U[67] 2.00 2 2 2.02 2.0 2.000 U[68] 3.00 3 3 3.01 3.0 3.000 U[69] 2.00 2 2 2.00 2.0 2.000 U[70] 3.00 3 3 2.97 3.0 3.000 U[71] 3.00 3 3 3.04 3.0 3.000 U[72] 1.00 3 3 2.92 3.0 3.000 U[73] 3.00 3 3 3.00 3.0 3.000 U[74] 2.00 2 2 2.04 2.0 2.000 U[75] 2.00 3 3 3.00 3.0 4.050 U[76] 2.00 2 2 2.14 2.0 4.000 U[77] 3.00 3 3 3.03 3.0 3.000 U[78] 3.00 3 3 3.00 3.0 3.000 U[79] 3.00 3 3 3.00 3.0 3.000 U[80] 3.00 3 3 3.00 3.0 3.000 U[81] 2.00 2 2 2.00 2.0 2.000 U[82] 2.00 2 3 2.75 3.0 3.000 U[83] 2.00 2 2 2.02 2.0 2.000 U[84] 3.00 3 3 3.00 3.0 3.000 U[85] 3.00 3 3 3.00 3.0 3.000 U[86] 3.00 3 3 3.00 3.0 3.000 U[87] 2.00 2 2 2.02 2.0 2.000 U[88] 2.00 2 2 2.12 2.0 4.000 U[89] 2.00 2 2 2.03 2.0 2.000 U[90] 2.00 2 2 2.02 2.0 2.000 U[91] 3.00 3 3 3.00 3.0 3.000 U[92] 2.00 2 2 1.99 2.0 2.000 U[93] 2.00 2 2 2.50 2.5 4.000 U[94] 2.00 2 2 2.07 2.0 3.050 U[95] 3.00 3 3 3.02 3.0 3.000 U[96] 2.00 2 2 2.01 2.0 2.000 U[97] 2.00 2 2 2.04 2.0 2.000 U[98] 2.00 2 2 2.00 2.0 2.000 U[99] 3.00 3 3 3.00 3.0 3.000 U[100] 2.00 2 2 2.00 2.0 2.000 > print(s, which = "group_param") ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Summary of the parameter estimates ----------------------------------------------------------------------- Parameters specific for cluster g=2: 2.5% 25% 50% Mean beta_num_ynum(2)[1] -2.38658976 -2.1020430 -1.93580343 -1.929746723 beta_num_ynum(2)[2] 1.03201417 1.2902806 1.43531117 1.421245731 prec_num_ynum(2) 1.19738441 1.6086339 1.75167555 1.739466562 sd_num_ynum(2) 0.67307721 0.7261678 0.75556736 0.771903127 var_num_ynum(2) 0.45303512 0.5273198 0.57088207 0.609729422 beta_poi_ypoi(2)[1] -0.96102801 -0.8404706 -0.72034324 -0.665121739 beta_poi_ypoi(2)[2] 0.41500122 1.5467770 1.74908980 1.643996374 beta_bin_ybin(2)[1] -1.29860941 -1.0530772 -0.76774957 -0.717080657 beta_bin_ybin(2)[2] 0.86033290 1.9519517 2.43689083 2.303758775 beta_ord_yord(2)[1] -1.02464280 -0.4391562 -0.05184670 -0.041745595 c_ord_yord(2)[1] -2.20494057 -1.7049194 -1.00609507 -1.210342314 c_ord_yord(2)[2] -1.44679557 -0.7556391 -0.01407816 -0.263705932 c_ord_yord(2)[3] -0.40107405 0.1868040 0.75028608 0.586763400 c_ord_yord(2)[4] 0.57665249 0.9460876 1.48034214 1.400769026 pi_ord_yord(2)[1] 0.09930770 0.1538239 0.26774948 0.243568728 pi_ord_yord(2)[2] 0.08243528 0.1556989 0.21512381 0.199421580 pi_ord_yord(2)[3] 0.12455013 0.1582375 0.18863629 0.191114322 pi_ord_yord(2)[4] 0.07696288 0.1190008 0.13991149 0.158945439 pi_ord_yord(2)[5] 0.10742199 0.1513387 0.18537575 0.206949931 beta_cat_ycat(2)[1,1] -0.46735182 0.7715670 1.09340535 0.932067674 beta_cat_ycat(2)[1,2] -0.78541919 -0.3182849 0.02976576 -0.001053881 beta_cat_ycat(2)[1,3] 0.35944227 0.5919205 0.79097164 0.773575344 beta_cat_ycat(2)[2,1] -1.60452935 -1.1753137 -0.66047167 -0.384972117 beta_cat_ycat(2)[2,2] -0.37905492 0.6660721 1.46795615 1.524346953 beta_cat_ycat(2)[2,3] -0.62157970 0.2426627 0.63116907 0.709866200 75% 97.5% beta_num_ynum(2)[1] -1.7983783 -1.46534767 beta_num_ynum(2)[2] 1.5860837 1.78348659 prec_num_ynum(2) 1.8963832 2.20737690 sd_num_ynum(2) 0.7884475 0.91406351 var_num_ynum(2) 0.6216509 0.83563139 beta_poi_ypoi(2)[1] -0.5437639 -0.01890735 beta_poi_ypoi(2)[2] 1.8238549 2.19519482 beta_bin_ybin(2)[1] -0.5532786 0.31996147 beta_bin_ybin(2)[2] 2.8247553 3.62586179 beta_ord_yord(2)[1] 0.4562251 0.87156933 c_ord_yord(2)[1] -0.7575504 -0.47881490 c_ord_yord(2)[2] 0.2056533 0.58955627 c_ord_yord(2)[3] 1.0103669 1.48733667 c_ord_yord(2)[4] 1.7241449 2.11735255 pi_ord_yord(2)[1] 0.3191794 0.38255237 pi_ord_yord(2)[2] 0.2511866 0.29120013 pi_ord_yord(2)[3] 0.2189842 0.26903215 pi_ord_yord(2)[4] 0.1849966 0.30432987 pi_ord_yord(2)[5] 0.2796724 0.35970329 beta_cat_ycat(2)[1,1] 1.3365912 1.57976766 beta_cat_ycat(2)[1,2] 0.3051652 0.91297041 beta_cat_ycat(2)[1,3] 0.9948967 1.24545494 beta_cat_ycat(2)[2,1] 0.1713736 1.46297761 beta_cat_ycat(2)[2,2] 2.5386930 3.27700498 beta_cat_ycat(2)[2,3] 1.1560043 1.83240975 Parameters specific for cluster g=3: 2.5% 25% 50% Mean beta_num_ynum(3)[1] 1.13829838 1.37478988 1.51467341 1.51168147 beta_num_ynum(3)[2] -2.00795073 -1.66877835 -1.44550126 -1.46721992 prec_num_ynum(3) 0.60078495 0.85335973 0.95257985 0.93806736 sd_num_ynum(3) 0.90455953 0.98022098 1.02459093 1.04377661 var_num_ynum(3) 0.81846272 0.96083320 1.04978852 1.09830139 beta_poi_ypoi(3)[1] 0.94118033 1.05490171 1.15300698 1.13546213 beta_poi_ypoi(3)[2] -2.15354581 -1.95795553 -1.83723031 -1.76784781 beta_bin_ybin(3)[1] -0.80365140 -0.33109344 -0.01787673 -0.03339514 beta_bin_ybin(3)[2] 1.94207093 3.09834055 3.57482024 3.68696976 beta_ord_yord(3)[1] -1.62795960 -0.60637542 -0.19368784 -0.29109813 c_ord_yord(3)[1] -2.74298967 -2.38276053 -2.16626375 -2.15478536 c_ord_yord(3)[2] -2.21899228 -1.59366757 -1.32841774 -1.34303749 c_ord_yord(3)[3] -1.55113632 -0.84449377 -0.52710624 -0.63261843 c_ord_yord(3)[4] -0.40432791 0.28432077 0.45478431 0.42637203 pi_ord_yord(3)[1] 0.06048577 0.08449706 0.10282134 0.10796720 pi_ord_yord(3)[2] 0.03544975 0.06819412 0.10622641 0.10741547 pi_ord_yord(3)[3] 0.07687060 0.12038251 0.13213318 0.13718845 pi_ord_yord(3)[4] 0.21442348 0.22345457 0.24731597 0.25031902 pi_ord_yord(3)[5] 0.28923809 0.34083751 0.38822386 0.39710986 beta_cat_ycat(3)[1,1] -2.32100546 -1.34651659 -0.53524859 -0.82678145 beta_cat_ycat(3)[1,2] -1.77113958 -1.46325479 -0.08734798 -0.38686440 beta_cat_ycat(3)[1,3] -0.76298786 -0.12356146 0.33636899 0.41693769 beta_cat_ycat(3)[2,1] 0.99960962 1.65866281 2.04127937 2.25067386 beta_cat_ycat(3)[2,2] -3.04514154 -1.60590981 -0.55462735 -0.08978714 beta_cat_ycat(3)[2,3] -1.07321274 -0.69107532 -0.06110159 0.09982089 75% 97.5% beta_num_ynum(3)[1] 1.6770998 1.91954654 beta_num_ynum(3)[2] -1.2817172 -0.88793081 prec_num_ynum(3) 1.0407635 1.22320350 sd_num_ynum(3) 1.0825163 1.29050066 var_num_ynum(3) 1.1718426 1.66569244 beta_poi_ypoi(3)[1] 1.2253186 1.28936890 beta_poi_ypoi(3)[2] -1.6492258 -1.06324793 beta_bin_ybin(3)[1] 0.2815469 0.65740405 beta_bin_ybin(3)[2] 4.3697320 5.67692325 beta_ord_yord(3)[1] 0.1354682 0.46209522 c_ord_yord(3)[1] -1.9231723 -1.47060896 c_ord_yord(3)[2] -1.0031387 -0.66774766 c_ord_yord(3)[3] -0.3418630 -0.07033748 c_ord_yord(3)[4] 0.6595642 0.89925679 pi_ord_yord(3)[1] 0.1275085 0.18685072 pi_ord_yord(3)[2] 0.1483091 0.18189886 pi_ord_yord(3)[3] 0.1611811 0.18537177 pi_ord_yord(3)[4] 0.2743868 0.30824910 pi_ord_yord(3)[5] 0.4293957 0.59971381 beta_cat_ycat(3)[1,1] -0.2821891 -0.01941793 beta_cat_ycat(3)[1,2] 0.5050425 0.80767058 beta_cat_ycat(3)[1,3] 1.0990405 1.47109252 beta_cat_ycat(3)[2,1] 2.8305036 4.75572142 beta_cat_ycat(3)[2,2] 1.8225334 2.54471578 beta_cat_ycat(3)[2,3] 0.7933736 1.63961993 > > # Restricting the rows by pattern > print(s, which = "group_param", pattern = "^beta_num") ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Summary of the parameter estimates ----------------------------------------------------------------------- Parameters specific for cluster g=2: 2.5% 25% 50% Mean 75% 97.5% beta_num_ynum(2)[1] -2.386590 -2.102043 -1.935803 -1.929747 -1.798378 -1.465348 beta_num_ynum(2)[2] 1.032014 1.290281 1.435311 1.421246 1.586084 1.783487 Parameters specific for cluster g=3: 2.5% 25% 50% Mean 75% beta_num_ynum(3)[1] 1.138298 1.374790 1.514673 1.511681 1.677100 beta_num_ynum(3)[2] -2.007951 -1.668778 -1.445501 -1.467220 -1.281717 97.5% beta_num_ynum(3)[1] 1.9195465 beta_num_ynum(3)[2] -0.8879308 > print(s, which = "group_param", pattern = "num") ----------------------------------------------------------------------- Chain 1 ----------------------------------------------------------------------- Summary of the parameter estimates ----------------------------------------------------------------------- Parameters specific for cluster g=2: 2.5% 25% 50% Mean 75% beta_num_ynum(2)[1] -2.3865898 -2.1020430 -1.9358034 -1.9297467 -1.7983783 beta_num_ynum(2)[2] 1.0320142 1.2902806 1.4353112 1.4212457 1.5860837 prec_num_ynum(2) 1.1973844 1.6086339 1.7516756 1.7394666 1.8963832 sd_num_ynum(2) 0.6730772 0.7261678 0.7555674 0.7719031 0.7884475 var_num_ynum(2) 0.4530351 0.5273198 0.5708821 0.6097294 0.6216509 97.5% beta_num_ynum(2)[1] -1.4653477 beta_num_ynum(2)[2] 1.7834866 prec_num_ynum(2) 2.2073769 sd_num_ynum(2) 0.9140635 var_num_ynum(2) 0.8356314 Parameters specific for cluster g=3: 2.5% 25% 50% Mean 75% beta_num_ynum(3)[1] 1.1382984 1.3747899 1.5146734 1.5116815 1.677100 beta_num_ynum(3)[2] -2.0079507 -1.6687784 -1.4455013 -1.4672199 -1.281717 prec_num_ynum(3) 0.6007849 0.8533597 0.9525799 0.9380674 1.040763 sd_num_ynum(3) 0.9045595 0.9802210 1.0245909 1.0437766 1.082516 var_num_ynum(3) 0.8184627 0.9608332 1.0497885 1.0983014 1.171843 97.5% beta_num_ynum(3)[1] 1.9195465 beta_num_ynum(3)[2] -0.8879308 prec_num_ynum(3) 1.2232035 sd_num_ynum(3) 1.2905007 var_num_ynum(3) 1.6656924 > > > > ### *