R Under development (unstable) (2026-04-07 r89803) -- "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. 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. > library(RSiena) > > # When new effects are added, the numbering of effects changes. > # This will have consequences for the output of set_interaction, > # and will require adaptation of parallel.Rout.save. > > ##test3 > mynet1 <- as_dependent_rsiena(array(c(tmp3, tmp4),dim=c(32, 32, 2))) > mydata <- make_data_rsiena(mynet1) > myeff<- make_specification(mydata) > print('test3') [1] "test3" > alg_alg <- set_algorithm_saom(cond=FALSE, seed=3, n3=50, nsub=2, findiff=TRUE) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 3.0740 ( 0.4229 ) 0.3149 2. eval outdegree (density) -1.1655 ( 0.1424 ) 0.0065 3. eval reciprocity 1.7954 ( 0.2956 ) -0.0069 Overall maximum convergence ratio: 0.3553 Total of 441 iteration steps. > (myeff <- set_effect(myeff, list(transTrip, cycle4))) effectNumber effectName shortName include fix test initialValue 1 20 transitive triplets transTrip TRUE FALSE FALSE 0 2 215 4 cycles (#) cycle4 TRUE FALSE FALSE 0 parm 1 0 2 1 effectName include fix test initialValue parm 1 basic rate parameter mynet1 TRUE FALSE FALSE 4.80941 0 2 outdegree (density) TRUE FALSE FALSE -0.56039 0 3 reciprocity TRUE FALSE FALSE 0.00000 0 4 transitive triplets TRUE FALSE FALSE 0.00000 0 5 4 cycles (#) TRUE FALSE FALSE 0.00000 1 > (myeff <- set_effect(myeff, cycle4, include=FALSE)) effectNumber effectName shortName include fix test initialValue parm 1 215 4 cycles (1) cycle4 FALSE FALSE FALSE 0 1 effectName include fix test initialValue parm 1 basic rate parameter mynet1 TRUE FALSE FALSE 4.80941 0 2 outdegree (density) TRUE FALSE FALSE -0.56039 0 3 reciprocity TRUE FALSE FALSE 0.00000 0 4 transitive triplets TRUE FALSE FALSE 0.00000 0 > ##test4 > print('test4') [1] "test4" > alg_alg <- set_algorithm_saom(cond=TRUE, condvarno=1, seed=3, n3=50, nsub=2, findiff=TRUE) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0 Rate parameter 3.1687 ( 0.4942 ) Other parameters: 1. eval outdegree (density) -1.7670 ( 0.3883 ) -0.0641 2. eval reciprocity 1.2846 ( 0.4058 ) -0.0064 3. eval transitive triplets 0.3319 ( 0.0845 ) 0.0180 Overall maximum convergence ratio: 0.1566 Total of 319 iteration steps. > ##test5 > mynet1 <- as_dependent_rsiena(array(c(tmp3,tmp4),dim=c(32,32,2))) > mydata <- make_data_rsiena(mynet1) > myeff<- make_specification(mydata) > print('test5') [1] "test5" > alg_alg <- set_algorithm_saom(cond=FALSE, seed=5, n3=50, nsub=2) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 3.0805 ( 0.6084 ) -0.1454 2. eval outdegree (density) -1.1473 ( 0.1609 ) -0.0251 3. eval reciprocity 1.7609 ( 0.3895 ) 0.1127 Overall maximum convergence ratio: 0.2373 Total of 569 iteration steps. > (myeff <- set_effect(myeff, list(recip, inPop))) effectNumber effectName shortName include fix test initialValue 1 14 reciprocity recip TRUE FALSE FALSE 0 2 77 indegree - popularity inPop TRUE FALSE FALSE 0 parm 1 0 2 0 effectName include fix test initialValue parm 1 basic rate parameter mynet1 TRUE FALSE FALSE 4.80941 0 2 outdegree (density) TRUE FALSE FALSE -0.56039 0 3 reciprocity TRUE FALSE FALSE 0.00000 0 4 indegree - popularity TRUE FALSE FALSE 0.00000 0 > (myeff <- set_effect(myeff, outAct, fix=TRUE, test=TRUE)) effectNumber effectName shortName include fix test initialValue 1 114 outdegree - activity outAct TRUE TRUE TRUE 0 parm 1 0 effectName include fix test initialValue parm 1 basic rate parameter mynet1 TRUE FALSE FALSE 4.80941 0 2 outdegree (density) TRUE FALSE FALSE -0.56039 0 3 reciprocity TRUE FALSE FALSE 0.00000 0 4 indegree - popularity TRUE FALSE FALSE 0.00000 0 5 outdegree - activity TRUE TRUE TRUE 0.00000 0 > (myeff <- set_interaction(myeff, list(recip, inPop), fix=TRUE, test=TRUE)) effectNumber effectName shortName include fix 1 14 reciprocity recip TRUE FALSE 2 77 indegree - popularity inPop TRUE FALSE 3 261 reciprocity x indegree - popularity unspInt TRUE TRUE test initialValue parm effect1 effect2 1 FALSE 0 0 0 0 2 FALSE 0 0 0 0 3 TRUE 0 0 14 77 effectName include fix test initialValue parm 1 basic rate parameter mynet1 TRUE FALSE FALSE 4.80941 0 2 outdegree (density) TRUE FALSE FALSE -0.56039 0 3 reciprocity TRUE FALSE FALSE 0.00000 0 4 indegree - popularity TRUE FALSE FALSE 0.00000 0 5 outdegree - activity TRUE TRUE TRUE 0.00000 0 6 reciprocity x indegree - popularity TRUE TRUE TRUE 0.00000 0 effect1 effect2 1 0 0 2 0 0 3 0 0 4 0 0 5 0 0 6 14 77 > alg_alg <- set_algorithm_saom(cond=FALSE, seed=5, n3=50, nsub=2) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg, returnDeps=TRUE) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 3.0683 ( 0.3886 ) 0.1642 2. eval outdegree (density) -1.4748 ( 0.4529 ) 0.1099 3. eval reciprocity 1.8375 ( 0.4070 ) 0.1469 4. eval indegree - popularity 0.0560 ( 0.0697 ) 0.1278 5. eval outdegree - activity 0.0000 ( NA ) -0.6803 6. eval reciprocity x indegree - popularity 0.0000 ( NA ) 0.5085 Overall maximum convergence ratio: 0.2187 Score test for 2 parameters: chi-squared = 10.01, p = 0.0067. Total of 382 iteration steps. > test_parameter(ans, method='score') Tested effects: outdegree - activity eval reciprocity x indegree - popularity eval chi-squared = 10.01, d.f. = 2; two-sided p = 0.007. > (goft <- test_gof(ans, IndegreeDistribution, verbose=TRUE, varName="mynet1", + test=NULL)) Detected 50 iterations and 1 group. Calculating auxiliary statistics for period 1 . Period 1 > Completed 50 calculations Estimating test statistic for model including outdegree - activity Estimating test statistic for model including reciprocity x indegree - popularity Siena Goodness of Fit ( IndegreeDistribution ), all periods ===== Monte Carlo Mahalanobis distance test p-value: 1 ----- One tailed test used (i.e. estimated probability of greater distance than observation). ----- Calculated joint MHD = ( 3.21 ) for current model. > summary(goft) Siena Goodness of Fit ( IndegreeDistribution ), all periods ===== Monte Carlo Mahalanobis distance test p-value: 1 ----- One tailed test used (i.e. estimated probability of greater distance than observation). ----- Calculated joint MHD = ( 3.21 ) for current model. One-step estimates and predicted Mahalanobis distances for modified models. **Model including outdegree - activity one-step basic rate parameter mynet1 3.211 outdegree (density) -3.160 reciprocity 2.751 indegree - popularity -0.020 outdegree - activity 0.158 reciprocity x indegree - popularity 0.000 MHD 4.995 **Model including reciprocity x indegree - popularity one-step basic rate parameter mynet1 3.565 outdegree (density) -3.768 reciprocity 7.759 indegree - popularity 0.416 outdegree - activity 0.000 reciprocity x indegree - popularity -0.945 MHD -0.801 -----> ##test6 > mynet1 <- as_dependent_rsiena(array(c(tmp3,tmp4),dim=c(32,32,2))) > mydata <- make_data_rsiena(mynet1) > myeff<- make_specification(mydata) > print('test6') [1] "test6" > alg_alg <- set_algorithm_saom(cond=FALSE, seed=5, n3=50, nsub=2) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 3.0805 ( 0.6084 ) -0.1454 2. eval outdegree (density) -1.1473 ( 0.1609 ) -0.0251 3. eval reciprocity 1.7609 ( 0.3895 ) 0.1127 Overall maximum convergence ratio: 0.2373 Total of 569 iteration steps. > myeff <- set_effect(myeff, recip, include=FALSE) effectNumber effectName shortName include fix test initialValue parm 1 14 reciprocity recip FALSE FALSE FALSE 0 0 > myeff <- set_effect(myeff, recip, type="endow") effectNumber effectName shortName include fix test initialValue parm 1 15 reciprocity recip TRUE FALSE FALSE 0 0 type 1 endow > myeff <- set_effect(myeff, recip, type="creation") effectNumber effectName shortName include fix test initialValue parm 1 16 reciprocity recip TRUE FALSE FALSE 0 0 type 1 creation > alg_alg <- set_algorithm_saom(cond=FALSE, seed=5, n3=50, nsub=2) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 3.1863 ( 1.0020 ) -0.2689 2. eval outdegree (density) -1.1153 ( 0.2082 ) 0.0224 3. endow reciprocity 2.4674 ( 0.8198 ) -0.0121 4. creat reciprocity 0.9547 ( 0.7225 ) -0.1711 Overall maximum convergence ratio: 0.3736 Total of 595 iteration steps. > test_parameter(ans, method='same', tested=3, tested2=4) Tested effects: reciprocity endow == reciprocity creation chi-squared = 1.79, d.f. = 1; standard error of linear combination = 1.13; one-sided Z = 1.34; two-sided p = 0.181. > ##test7 > mynet1 <- as_dependent_rsiena(array(c(tmp3,tmp4),dim=c(32,32,2))) > mydata <- make_data_rsiena(mynet1) > myeff<- make_specification(mydata) > print('test7') [1] "test7" > alg_alg <- set_algorithm_saom(cond=FALSE, seed=5, n3=50, nsub=2, + diagonalize=0.5) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 3.0537 ( 1.1043 ) 0.1719 2. eval outdegree (density) -1.1479 ( 0.2592 ) -0.1018 3. eval reciprocity 1.7860 ( 0.3821 ) 0.0983 Overall maximum convergence ratio: 0.2958 Total of 537 iteration steps. > ##test8 > print('test8') [1] "test8" > alg_alg <- set_algorithm_saom(cond=TRUE, condvarno=1, seed=5, n3=50, nsub=1) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0 Rate parameter 3.1232 ( 0.5758 ) Other parameters: 1. eval outdegree (density) -1.1569 ( 0.1554 ) 0.1198 2. eval reciprocity 1.8304 ( 0.4047 ) 0.1841 Overall maximum convergence ratio: 0.1881 Total of 322 iteration steps. > ##test9 > mynet1 <- as_dependent_rsiena(array(c(s501, s502, s503), dim=c(50, 50, 3))) > mynet2 <- as_dependent_rsiena(s50a,type='behavior') > mydata <- make_data_rsiena(mynet1, mynet2) > myeff <- make_specification(mydata) > myeff <- set_effect(myeff, linear, depvar="mynet2", initialValue=0.34699930338) effectNumber effectName shortName include fix test initialValue 1 501 mynet2 linear shape linear TRUE FALSE FALSE 0.347 parm 1 0 > myeff <- set_effect(myeff, avAlt, depvar="mynet2", covar1="mynet1") effectNumber effectName shortName include fix test initialValue 1 590 mynet2 average alter avAlt TRUE FALSE FALSE 0 parm 1 0 > ##test10 > print('test10') [1] "test10" > alg_alg <- set_algorithm_saom(cond=TRUE, condvarno=1, seed=5, n3=50, nsub=1) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > alg_alg2 <- set_algorithm_saom(cond=TRUE, condvarno=1, seed=5, n3=50, nsub=1, + splitDepvars=1) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg2) > ##, verbose=TRUE) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0.1 Rate parameter cond. variable period 1 5.8715 ( 0.9109 ) 0.2 Rate parameter cond. variable period 2 4.6876 ( 0.6945 ) Other parameters: Network Dynamics 1. eval outdegree (density) -2.3814 ( 0.1861 ) -0.0899 2. eval reciprocity 2.8547 ( 0.2796 ) -0.1773 Behavior Dynamics 3. rate rate mynet2 (period 1) 1.2908 ( 0.4995 ) 0.0651 4. rate rate mynet2 (period 2) 1.8263 ( 1.1275 ) 0.2198 5. eval mynet2 linear shape 0.4162 ( 0.3652 ) 0.0275 6. eval mynet2 quadratic shape -0.5562 ( 0.4516 ) -0.1204 7. eval mynet2 average alter 1.2961 ( 1.1875 ) -0.0742 Overall maximum convergence ratio: 0.4851 Total of 335 iteration steps. > ##test11 > print('test11') [1] "test11" > alg_model <- set_model_saom(behModelType=c(mynet2=2)) > alg_alg <- set_algorithm_saom(seed=6, n3=50, nsub=1) > (ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_model=alg_model, control_algo=alg_alg)) Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Network Dynamics 1. rate constant mynet1 rate (period 1) 5.8862 ( 1.7412 ) -0.0875 2. rate constant mynet1 rate (period 2) 4.5183 ( 1.2772 ) 0.1575 3. eval outdegree (density) -2.3671 ( 0.1068 ) -0.0348 4. eval reciprocity 2.8201 ( 0.2726 ) 0.0175 Behavior Dynamics 5. rate rate mynet2 (period 1) 1.3051 ( 0.7125 ) -0.1583 6. rate rate mynet2 (period 2) 1.7674 ( 0.6500 ) -0.0774 7. eval mynet2 linear shape 0.3716 ( 0.3944 ) -0.0150 8. eval mynet2 quadratic shape -0.5753 ( 0.4137 ) -0.0412 9. eval mynet2 average alter 1.2104 ( 0.9551 ) 0.0625 Overall maximum convergence ratio: 0.3450 Behavioral Model Type: mynet2 : Boundary-absorbing behavior model Total of 340 iteration steps. > ##test12 > print('test12') [1] "test12" > use<- 1:30 > mynet1 <- as_dependent_rsiena(array(c(s501[use,], s502[use,], s503[use,]), + dim=c(length(use), 50,3)), type='bipartite', + nodeSet=c('Senders','receivers')) > receivers <- as_nodeset_rsiena(50,'receivers') > senders <- as_nodeset_rsiena(30,'Senders') > myvar1 <- as_covariate_rsiena(s50a[1:30,2], nodeSet='Senders') > mydata <- make_data_rsiena(mynet1, myvar1, nodeSets=list(senders, receivers)) > myeff <- make_specification(mydata) > myeff <- set_effect(myeff, inPop) effectNumber effectName shortName include fix test initialValue 1 18 indegree - popularity inPop TRUE FALSE FALSE 0 parm 1 0 > myeff <- set_effect(myeff, altInDist2, covar1="myvar1", parameter=1) effectNumber effectName shortName include fix test 1 119 myvar1 in-alter dist 2 altInDist2 TRUE FALSE FALSE initialValue parm 1 0 1 > alg_alg <- set_algorithm_saom(seed=1, n3=50, nsub=2) > ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg) > ans Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0.1 Rate parameter period 1 3.6956 ( 0.5378 ) 0.2 Rate parameter period 2 2.8639 ( 0.5543 ) Other parameters: 1. eval outdegree (density) 2.5056 ( 2.1342 ) 0.5304 2. eval indegree - popularity -3.3120 ( 1.1266 ) 0.6913 3. eval myvar1 in-alter dist 2 31.4680 ( 11.4585 ) -2.1940 Overall maximum convergence ratio: 6.1667 Total of 588 iteration steps. > tt <- test_time(ans) > summary(tt) Joint significance test of time heterogeneity: chi-squared = 12.47, d.f. = 3, p= 0.0059, where H0: The following parameters are zero: (1) (*)Dummy2:outdegree (density) (2) (*)Dummy2:indegree - popularity (3) (*)Dummy2:myvar1 in-alter dist 2 Individual significance tests and one-step estimators: Initial Est. One Step Est. p-Value outdegree (density) 2.5056 -24.8109 0.2400 indegree - popularity -3.3120 26.6232 0.0030 myvar1 in-alter dist 2 31.4680 -290.8078 0.0060 (*)Dummy2:outdegree (density) 0.0000 43.0380 0.2480 (*)Dummy2:indegree - popularity 0.0000 -39.2011 0.5460 (*)Dummy2:myvar1 in-alter dist 2 0.0000 379.2771 0.0760 Effect-wise joint significance tests (i.e. each effect across all dummies): chi-sq. df p-value outdegree (density) 1.33 1 0.249 indegree - popularity 0.37 1 0.543 myvar1 in-alter dist 2 3.14 1 0.076 Period-wise joint significance tests (i.e. each period across all parameters): chi-sq. df p-value Period 1 12.47 3 0.006 Period 2 12.47 3 0.006 Use the following indices for plotting: (1) outdegree (density) (2) indegree - popularity (3) myvar1 in-alter dist 2 If you would like to fit time dummies to your model, use the includeTimeDummy function. Type "?test_time" for more information on this output. > ##test13 > print('test13') [1] "test13" > use<- 1:30 > mynet1 <- as_dependent_rsiena(array(c(s502[,use], s503[,use]), + dim=c(50, length(use), 2)), type='bipartite', + nodeSet=c('Senders','receivers')) > receivers <- as_nodeset_rsiena(30,'receivers') > senders <- as_nodeset_rsiena(50,'Senders') > myvar1 <- as_covariate_rsiena(s50a[1:50,2], nodeSet='Senders') > mydata <- make_data_rsiena(mynet1, myvar1, nodeSets=list(senders, receivers)) > myeff <- make_specification(mydata) > myeff <- set_effect(myeff, altInDist2, covar1="myvar1", parameter=1) effectNumber effectName shortName include fix test 1 118 myvar1 in-alter dist 2 altInDist2 TRUE FALSE FALSE initialValue parm 1 0 1 > myeff <- set_effect(myeff, egoX, covar1="myvar1") effectNumber effectName shortName include fix test initialValue parm 1 97 myvar1 ego egoX TRUE FALSE FALSE 0 0 > alg_alg <- set_algorithm_saom(seed=1, n3=50, nsub=2) > (ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0 Rate parameter 1.9481 ( 0.3096 ) Other parameters: 1. eval outdegree (density) -1.8277 ( 0.2233 ) -0.1497 2. eval myvar1 ego 0.2986 ( 0.1972 ) -0.0027 3. eval myvar1 in-alter dist 2 -0.0209 ( 0.3079 ) 0.0945 Overall maximum convergence ratio: 0.3041 Total of 535 iteration steps. > ##test14 > print('test14') [1] "test14" > net <- as_dependent_rsiena(array(c(tmp3, tmp4), dim=c(32, 32, 2))) > dataset <- make_data_rsiena(net) > myeff <- make_specification(dataset) > myeff <- set_effect(myeff, inPop) effectNumber effectName shortName include fix test initialValue 1 77 indegree - popularity inPop TRUE FALSE FALSE 0 parm 1 0 > alg_alg <- set_algorithm_saom(maxlike=TRUE, cond=FALSE, seed=15, n3=20, nsub=1, + diagonalize=0, mult=1) > (ans <- siena(data=dataset, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimated by Maximum Likelihood Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter net 3.7816 ( 0.4178 ) 0.6167 2. eval outdegree (density) -1.5840 ( 0.3353 ) 2.9602 3. eval reciprocity 1.8606 ( 0.2314 ) 1.4786 4. eval indegree - popularity 0.1082 ( 0.0440 ) 2.5318 Overall maximum convergence ratio: 4.7198 Total of 266 iteration steps. > ##test 15 > print('test15') [1] "test15" > mynet1 <- as_dependent_rsiena(array(c(s501, s502, s503), dim=c(50, 50, 3))) > mynet2 <- as_dependent_rsiena(s50a,type='behavior') > mydata <- make_data_rsiena(mynet1, mynet2) > myeff <- make_specification(mydata) > (myeff <- set_effect(myeff, transTrip)) effectNumber effectName shortName include fix test initialValue 1 22 transitive triplets transTrip TRUE FALSE FALSE 0 parm 1 0 name effectName include fix test initialValue parm 1 mynet1 constant mynet1 rate (period 1) TRUE FALSE FALSE 4.69604 0 2 mynet1 constant mynet1 rate (period 2) TRUE FALSE FALSE 4.32885 0 3 mynet1 outdegree (density) TRUE FALSE FALSE -1.46770 0 4 mynet1 reciprocity TRUE FALSE FALSE 0.00000 0 5 mynet1 transitive triplets TRUE FALSE FALSE 0.00000 0 6 mynet2 rate mynet2 (period 1) TRUE FALSE FALSE 0.70571 0 7 mynet2 rate mynet2 (period 2) TRUE FALSE FALSE 0.84939 0 8 mynet2 mynet2 linear shape TRUE FALSE FALSE 0.32237 0 9 mynet2 mynet2 quadratic shape TRUE FALSE FALSE 0.00000 0 > (myeff <- set_effect(myeff, list(egoX, simX), covar1="mynet2")) effectNumber effectName shortName include fix test initialValue 1 278 mynet2 ego egoX TRUE FALSE FALSE 0 2 324 mynet2 similarity simX TRUE FALSE FALSE 0 parm 1 0 2 0 name effectName include fix test initialValue parm 1 mynet1 constant mynet1 rate (period 1) TRUE FALSE FALSE 4.69604 0 2 mynet1 constant mynet1 rate (period 2) TRUE FALSE FALSE 4.32885 0 3 mynet1 outdegree (density) TRUE FALSE FALSE -1.46770 0 4 mynet1 reciprocity TRUE FALSE FALSE 0.00000 0 5 mynet1 transitive triplets TRUE FALSE FALSE 0.00000 0 6 mynet1 mynet2 ego TRUE FALSE FALSE 0.00000 0 7 mynet1 mynet2 similarity TRUE FALSE FALSE 0.00000 0 8 mynet2 rate mynet2 (period 1) TRUE FALSE FALSE 0.70571 0 9 mynet2 rate mynet2 (period 2) TRUE FALSE FALSE 0.84939 0 10 mynet2 mynet2 linear shape TRUE FALSE FALSE 0.32237 0 11 mynet2 mynet2 quadratic shape TRUE FALSE FALSE 0.00000 0 > (myeff <- set_effect(myeff, avSim, depvar="mynet2", covar1="mynet1")) effectNumber effectName shortName include fix test 1 534 mynet2 average similarity avSim TRUE FALSE FALSE initialValue parm 1 0 0 name effectName include fix test initialValue parm 1 mynet1 constant mynet1 rate (period 1) TRUE FALSE FALSE 4.69604 0 2 mynet1 constant mynet1 rate (period 2) TRUE FALSE FALSE 4.32885 0 3 mynet1 outdegree (density) TRUE FALSE FALSE -1.46770 0 4 mynet1 reciprocity TRUE FALSE FALSE 0.00000 0 5 mynet1 transitive triplets TRUE FALSE FALSE 0.00000 0 6 mynet1 mynet2 ego TRUE FALSE FALSE 0.00000 0 7 mynet1 mynet2 similarity TRUE FALSE FALSE 0.00000 0 8 mynet2 rate mynet2 (period 1) TRUE FALSE FALSE 0.70571 0 9 mynet2 rate mynet2 (period 2) TRUE FALSE FALSE 0.84939 0 10 mynet2 mynet2 linear shape TRUE FALSE FALSE 0.32237 0 11 mynet2 mynet2 quadratic shape TRUE FALSE FALSE 0.00000 0 12 mynet2 mynet2 average similarity TRUE FALSE FALSE 0.00000 0 > (myeff <- includeGMoMStatistics(myeff, simX_gmm, covar1="mynet2")) name shortName type include 1 mynet1 simX_gmm gmm TRUE Effects and statistics for estimation by the Generalized Method of Moments Effects name effectName include fix test initialValue parm 1 mynet1 constant mynet1 rate (period 1) TRUE FALSE FALSE 4.69604 0 2 mynet1 constant mynet1 rate (period 2) TRUE FALSE FALSE 4.32885 0 3 mynet1 outdegree (density) TRUE FALSE FALSE -1.46770 0 4 mynet1 reciprocity TRUE FALSE FALSE 0.00000 0 5 mynet1 transitive triplets TRUE FALSE FALSE 0.00000 0 6 mynet1 mynet2 ego TRUE FALSE FALSE 0.00000 0 7 mynet1 mynet2 similarity TRUE FALSE FALSE 0.00000 0 8 mynet2 rate mynet2 (period 1) TRUE FALSE FALSE 0.70571 0 9 mynet2 rate mynet2 (period 2) TRUE FALSE FALSE 0.84939 0 10 mynet2 mynet2 linear shape TRUE FALSE FALSE 0.32237 0 11 mynet2 mynet2 quadratic shape TRUE FALSE FALSE 0.00000 0 12 mynet2 mynet2 average similarity TRUE FALSE FALSE 0.00000 0 type 1 rate 2 rate 3 eval 4 eval 5 eval 6 eval 7 eval 8 rate 9 rate 10 eval 11 eval 12 eval Regular and GMoM statistics name effectName Statistic 1 mynet1 constant mynet1 rate (period 1) Regular 2 mynet1 constant mynet1 rate (period 2) Regular 3 mynet1 outdegree (density) Regular 4 mynet1 reciprocity Regular 5 mynet1 transitive triplets Regular 6 mynet1 mynet2 ego Regular 7 mynet1 mynet2 similarity Regular 8 mynet2 rate mynet2 (period 1) Regular 9 mynet2 rate mynet2 (period 2) Regular 10 mynet2 mynet2 linear shape Regular 11 mynet2 mynet2 quadratic shape Regular 12 mynet2 mynet2 average similarity Regular 13 mynet1 mynet2 similarity GMoM > alg_alg <- set_algorithm_saom(gmm=TRUE, seed=6, n3=100, nsub=1) > (ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimated by Generalized Method of Moments Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Network Dynamics 1. rate constant mynet1 rate (period 1) 5.5632 ( 1.2970 ) -1.0930 2. rate constant mynet1 rate (period 2) 4.3687 ( 0.6412 ) -1.6447 3. eval outdegree (density) -2.5981 ( 0.1535 ) 1.1781 4. eval reciprocity 2.6870 ( 0.2324 ) 1.8862 5. eval transitive triplets 0.3907 ( 0.0737 ) -2.3790 6. eval mynet2 ego 0.0371 ( 0.0979 ) 0.6639 7. eval mynet2 similarity 1.1255 ( 0.4169 ) 1.5314 Behavior Dynamics 8. rate rate mynet2 (period 1) 1.1603 ( 0.4551 ) 0.1277 9. rate rate mynet2 (period 2) 1.6443 ( 0.4689 ) 0.1219 10. eval mynet2 linear shape 0.4098 ( 0.1531 ) 0.4140 11. eval mynet2 quadratic shape -0.1597 ( 0.1557 ) 0.4469 12. eval mynet2 average similarity 0.7157 ( 2.2581 ) -0.6514 Overall maximum convergence ratio: 5.3403 Total of 605 iteration steps. > ##test16 > print('test16') [1] "test16" > set.seed(123) # simulate behavior data according to dZ(t) = [-0.1 Z + 1] dt + 1 dW(t) > y1 <- rnorm(50, 0,3) > y2 <- exp(-0.1) * y1 + (1-exp(-0.1)) * 1/ -0.1 + rnorm(50, 0, (exp(-0.2)- 1) / -0.2 * 1^2) > friend <- as_dependent_rsiena(array(c(s501, s502), dim = c(50,50,2))) > behavior <- as_dependent_rsiena(matrix(c(y1,y2), 50,2), type = "continuous") > (mydata <- make_data_rsiena(friend, behavior)) Dependent variables: friend, behavior Number of observations: 2 Nodeset Actors Number of nodes 50 Dependent variable friend Type oneMode Observations 2 Nodeset Actors Densities 0.046 0.047 Dependent variable behavior Type continuous Observations 2 Nodeset Actors Range -6.242 - 6.507 > (myeff <- make_specification(mydata, onePeriodSde = TRUE)) SDE init parameters: -0.1117176 -0.864023 0.8576913 SDE par stand errors: 0.04669358 0.1223113 0.08791327 name effectName include fix test initialValue parm 1 friend basic rate parameter friend TRUE FALSE FALSE 4.69604 0 2 friend outdegree (density) TRUE FALSE FALSE -1.48852 0 3 friend reciprocity TRUE FALSE FALSE 0.00000 0 4 sde scale parameter period 1 TRUE TRUE FALSE 1.00000 0 5 behavior wiener (behavior.behavior) TRUE FALSE FALSE 0.85769 0 6 behavior feedback from behavior TRUE FALSE FALSE -0.11172 0 7 behavior intercept TRUE FALSE FALSE -0.86402 0 > alg_alg <- set_algorithm_saom(seed=321, n3=20, nsub=1) > (ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) SDE init parameters: -0.1117176 -0.864023 0.8576913 SDE par stand errors: 0.04669358 0.1223113 0.08791327 Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Network Dynamics 1. rate basic rate parameter friend 5.5455 ( 1.3505 ) 0.1743 2. eval outdegree (density) -2.2776 ( 0.1270 ) -0.2121 3. eval reciprocity 2.4902 ( 0.2396 ) -0.1214 Continuous Behavior Dynamics 4. eval wiener (behavior.behavior) 0.8424 ( 0.0167 ) -0.2656 5. eval feedback from behavior -0.1108 ( 0.0941 ) 0.1166 6. eval intercept -0.8651 ( 0.1500 ) 0.2041 7. rate scale parameter period 1 1.0000 ( NA ) -0.2656 Overall maximum convergence ratio: 0.5077 Total of 305 iteration steps. > ##test17 > print('test17') [1] "test17" > mynet <- sienaNet(array(c(s501, s502), dim=c(50, 50, 2))) > sm1 <- 1*(s50s[,2] >= 2) > sm2 <- 1*(s50s[,3] >= 2) > sm2 <- pmax(sm1,sm2) > sm2[c(33,28,29,44)] <- 1 > mybeh <- as_dependent_rsiena(cbind(sm1,sm2), type="behavior") > (mydata <- make_data_rsiena(mynet, mybeh)) For dependent variable mybeh, in some periods, there are only increases, or only decreases. This will be respected in the simulations. If this is not desired, use allowOnly=FALSE when creating the dependent variable. Dependent variables: mynet, mybeh Number of observations: 2 Nodeset Actors Number of nodes 50 Dependent variable mynet Type oneMode Observations 2 Nodeset Actors Densities 0.046 0.047 Dependent variable mybeh Type behavior Observations 2 Nodeset Actors Range 0 - 1 "uponly": mybeh: all periods > myeff <- make_specification(mydata) > (myeff <- set_effect(myeff, avExposure, type="rate", depvar="mybeh", + covar1="mynet", parameter=2)) effectNumber effectName shortName include fix 1 489 average exposure effect on rate mybeh avExposure TRUE FALSE test initialValue parm 1 FALSE 0 2 name effectName include fix test initialValue 1 mynet basic rate parameter mynet TRUE FALSE FALSE 4.69604 2 mynet outdegree (density) TRUE FALSE FALSE -1.48852 3 mynet reciprocity TRUE FALSE FALSE 0.00000 4 mybeh rate mybeh period 1 TRUE FALSE FALSE 0.26000 5 mybeh average exposure effect on rate mybeh TRUE FALSE FALSE 0.00000 parm 1 0 2 0 3 0 4 0 5 2 > alg_alg <- set_algorithm_saom(seed=1234, n3=10, nsub=1, firstg=0.001) > (ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Network Dynamics 1. rate basic rate parameter mynet 5.0343 ( 2.6745 ) 2.9531 2. eval outdegree (density) -1.5767 ( 0.2534 ) 2.3103 3. eval reciprocity 0.4645 ( 0.5094 ) -6.9043 Behavior Dynamics 4. rate rate mybeh period 1 0.3748 ( 1.5645 ) -1.2179 5. rate average exposure effect on rate mybeh 0.4451 ( 0.3627 ) -3.4187 Overall maximum convergence ratio: 17.2538 Total of 290 iteration steps. > ##test18 > print('test18') [1] "test18" > mynet1 <- as_dependent_rsiena(array(c(tmp3, tmp4), dim=c(32, 32, 2))) > cova <- as_covariate_rsiena(1:32) > cova2 <- as_covariate_rsiena(rep(0,32), warn=FALSE) > mydata <- make_data_rsiena(mynet1, cova) > mydata2 <- make_data_rsiena(mynet1, cova=cova2) > mygroup <- make_group_rsiena(list(mydata,mydata2)) > myeff <- make_specification(mygroup) > myeff <- set_effect(myeff, simX, covar1="cova") effectNumber effectName shortName include fix test initialValue parm 1 324 cova similarity simX TRUE FALSE FALSE 0 0 > alg_alg <- set_algorithm_saom(seed=1293, n3=10, nsub=1) > (ans <- siena(data=mygroup, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0.1 Rate parameter period 1 2.9223 ( 0.3564 ) 0.2 Rate parameter period 2 3.4189 ( 0.4703 ) Other parameters: 1. eval outdegree (density) -1.1282 ( 0.2481 ) 0.1531 2. eval reciprocity 1.8043 ( 0.5071 ) 0.1914 3. eval cova similarity -0.0338 ( 0.2107 ) 0.1075 Overall maximum convergence ratio: 0.2479 Total of 285 iteration steps. > ##test19 > print('test19') [1] "test19" > mynet <- as_dependent_rsiena(array(c(s501, s502), dim=c(50, 50, 2))) > alc <- as_covariate_rsiena(s50a[,1]) > smoke <- as_covariate_rsiena(s50s[,1]) > mydata <- make_data_rsiena(mynet, alc, smoke) > myeff <- make_specification(mydata) > myeff <- set_effect(myeff, gwespFF) effectNumber effectName shortName include fix test 1 55 GWESP I -> K -> J (69) gwespFF TRUE FALSE FALSE initialValue parm 1 0 69 > myeff <- set_effect(myeff, gwespFF, parameter=20) effectNumber effectName shortName include fix test 1 55 GWESP I -> K -> J (20) gwespFF TRUE FALSE FALSE initialValue parm 1 0 20 > myeff <- set_effect(myeff, outTrunc, parameter=2, include=FALSE) effectNumber effectName shortName include fix test initialValue 1 132 outdegree-trunc(2) outTrunc FALSE FALSE FALSE 0 parm 1 2 > myeff <- set_interaction(myeff, list(outTrunc, egoX, egoX), covar1=c("", + "smoke", "alc")) effectNumber effectName shortName include fix 1 132 outdegree-trunc(2) outTrunc FALSE FALSE 2 278 alc ego egoX FALSE FALSE 3 462 smoke ego egoX FALSE FALSE 4 631 smoke ego x alc ego x outdegree-trunc(2) unspInt TRUE FALSE test initialValue parm effect1 effect2 effect3 1 FALSE 0 2 0 0 0 2 FALSE 0 0 0 0 0 3 FALSE 0 0 0 0 0 4 FALSE 0 0 132 462 278 > alg_alg <- set_algorithm_saom(seed=1943, n3=20, nsub=1) > (ans <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio Rate parameters: 0 Rate parameter 6.3459 ( 1.1706 ) Other parameters: 1. eval outdegree (density) -2.8004 ( 0.2537 ) -0.3334 2. eval reciprocity 2.2810 ( 0.4770 ) -0.2645 3. eval GWESP I -> K -> J (20) 1.7122 ( 0.5923 ) -0.3894 4. eval smoke ego x alc ego x outdegree-trunc(2) 0.5763 ( 0.5052 ) -0.1619 Overall maximum convergence ratio: 0.5173 Total of 297 iteration steps. > ##test20 > print('test20') [1] "test20" > mynet1 <- as_dependent_rsiena(array(c(s501, s502), dim=c(50, 50, 2))) > mynet2 <- as_dependent_rsiena(array(c(s503, s502), dim=c(50, 50, 2))) > mydata <- make_data_rsiena(mynet1, mynet2) > myeff <- make_specification(mydata) > myeff <- set_effect(myeff, crprod, depvar="mynet2", covar1="mynet1") effectNumber effectName shortName include fix test initialValue parm 1 754 mynet2: mynet1 crprod TRUE FALSE FALSE 0 0 > myeff <- set_effect(myeff, from, depvar="mynet1", covar1="mynet2") effectNumber effectName shortName include fix test 1 367 mynet1: from mynet2 agreement (0) from TRUE FALSE FALSE initialValue parm 1 0 0 > (myeff <- includeGMoMStatistics(myeff, from_gmm, depvar='mynet1', + covar1='mynet2')) name shortName type include 1 mynet1 from_gmm gmm TRUE Effects and statistics for estimation by the Generalized Method of Moments Effects name effectName include fix test initialValue 1 mynet1 basic rate parameter mynet1 TRUE FALSE FALSE 4.69604 2 mynet1 mynet1: outdegree (density) TRUE FALSE FALSE -1.48852 3 mynet1 mynet1: reciprocity TRUE FALSE FALSE 0.00000 4 mynet1 mynet1: from mynet2 agreement (0) TRUE FALSE FALSE 0.00000 5 mynet2 basic rate parameter mynet2 TRUE FALSE FALSE 4.32885 6 mynet2 mynet2: outdegree (density) TRUE FALSE FALSE -1.53104 7 mynet2 mynet2: reciprocity TRUE FALSE FALSE 0.00000 8 mynet2 mynet2: mynet1 TRUE FALSE FALSE 0.00000 parm type 1 0 rate 2 0 eval 3 0 eval 4 0 eval 5 0 rate 6 0 eval 7 0 eval 8 0 eval Regular and GMoM statistics name effectName Statistic 1 mynet1 basic rate parameter mynet1 Regular 2 mynet1 mynet1: outdegree (density) Regular 3 mynet1 mynet1: reciprocity Regular 4 mynet1 mynet1: from mynet2 agreement (0) Regular 5 mynet2 basic rate parameter mynet2 Regular 6 mynet2 mynet2: outdegree (density) Regular 7 mynet2 mynet2: reciprocity Regular 8 mynet2 mynet2: mynet1 Regular 9 mynet1 mynet1: from mynet2 agreement (#) GMoM > alg_alg <- set_algorithm_saom(seed=1293, n3=50, nsub=2) > (ans <- siena(data=mydata, effects=myeff[myeff$type != "gmm", ], batch=TRUE, + silent=TRUE, control_algo=alg_alg)) Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 5.5596 ( 2.5822 ) 0.0653 2. eval mynet1: outdegree (density) -2.5572 ( 0.2501 ) 0.0435 3. eval mynet1: reciprocity 2.0302 ( 0.8754 ) 0.1185 4. eval mynet1: from mynet2 agreement (0) 1.3237 ( 0.2420 ) 0.0714 5. rate basic rate parameter mynet2 4.6888 ( 2.8648 ) 0.0094 6. eval mynet2: outdegree (density) -2.8217 ( 0.3759 ) 0.1110 7. eval mynet2: reciprocity 1.8266 ( 0.4459 ) 0.1225 8. eval mynet2: mynet1 3.2305 ( 0.5184 ) 0.0690 Overall maximum convergence ratio: 0.2416 Total of 593 iteration steps. > alg_alg <- set_algorithm_saom(gmm=TRUE, seed=1293, n3=50, nsub=2) > (ans1 <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + control_algo=alg_alg)) Estimated by Generalized Method of Moments Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 5.4255 ( 1.0817 ) -0.2549 2. eval mynet1: outdegree (density) -2.5970 ( 0.2717 ) 0.1179 3. eval mynet1: reciprocity 1.9354 ( 0.4496 ) 0.4581 4. eval mynet1: from mynet2 agreement (0) 1.4695 ( 0.2798 ) 0.5470 5. rate basic rate parameter mynet2 4.4444 ( 1.3604 ) -0.1299 6. eval mynet2: outdegree (density) -2.9751 ( 0.4063 ) -0.1273 7. eval mynet2: reciprocity 1.9088 ( 0.6160 ) 0.2121 8. eval mynet2: mynet1 3.5549 ( 0.8794 ) -0.0522 Overall maximum convergence ratio: 1.3483 Total of 405 iteration steps. > alg_alg <- set_algorithm_saom(gmm=TRUE, seed=1293, n3=50, nsub=2) > (ans2 <- siena(data=mydata, effects=myeff, batch=TRUE, silent=TRUE, + prevAns=ans1, control_algo=alg_alg)) Estimated by Generalized Method of Moments Estimates, standard errors and convergence t-ratios Estimate Standard Convergence Error t-ratio 1. rate basic rate parameter mynet1 5.0506 ( 1.2471 ) 0.3424 2. eval mynet1: outdegree (density) -2.4559 ( 0.1976 ) 0.4815 3. eval mynet1: reciprocity 1.6352 ( 0.3341 ) -0.0907 4. eval mynet1: from mynet2 agreement (0) 1.4281 ( 0.3039 ) -0.1970 5. rate basic rate parameter mynet2 4.3001 ( 1.2688 ) -0.2889 6. eval mynet2: outdegree (density) -2.6547 ( 0.4704 ) 0.0031 7. eval mynet2: reciprocity 1.4674 ( 0.2944 ) -0.7729 8. eval mynet2: mynet1 3.2960 ( 0.9690 ) -0.3996 Overall maximum convergence ratio: 2.2389 Total of 590 iteration steps. > > ##test21 > # Run simple test model ---- > mynet <- as_dependent_rsiena(array(c(s501, s502, s503), dim = c(50, 50, 3))) > mydata <- make_data_rsiena(mynet) > mymodel <- make_specification(mydata) > ## TransitiveTriplets model > mymodel <- set_effect(mymodel, transTrip, depvar="mynet") effectNumber effectName shortName include fix test initialValue 1 21 transitive triplets transTrip TRUE FALSE FALSE 0 parm 1 0 > # Test returnChangeContributions when running siena directly ---- > > print('test21') [1] "test21" > alg_out <- set_output_saom(returnChangeContributions=TRUE) > alg_alg <- set_algorithm_saom(cond=FALSE, seed=42, n3=60, nsub=1) > ans <- siena(data=mydata, effects=mymodel, batch=TRUE, silent=TRUE, + control_algo=alg_alg, control_out=alg_out) ================================================================= ==2006122==ERROR: AddressSanitizer: stack-use-after-scope on address 0x7bc1b09a3521 at pc 0x563c6b779a42 bp 0x7fff24780d30 sp 0x7fff247804e0 READ of size 6 at 0x7bc1b09a3521 thread T0 #0 0x563c6b779a41 in strcmp /home/runner/work/llvm-project/llvm-project/compiler-rt/lib/asan/../sanitizer_common/sanitizer_common_interceptors.inc:505:5 #1 0x7bc19da2f3ff in siena::getChangeContributionsList(siena::Chain const&, SEXPREC*) /data/gannet/ripley/R/packages/tests-clang-ASAN/RSiena/src/siena07utilities.cpp:909:9 #2 0x7bc19da19943 in forwardModel /data/gannet/ripley/R/packages/tests-clang-ASAN/RSiena/src/siena07models.cpp:429:36 #3 0x563c6b9c69be in R_doDotCall /data/gannet/ripley/R/svn/R-devel/src/main/dotcode.c #4 0x563c6b9cf585 in do_dotcall /data/gannet/ripley/R/svn/R-devel/src/main/dotcode.c:1437:11 #5 0x563c6ba7efca in bcEval_loop /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:8132:14 #6 0x563c6ba71dd4 in bcEval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:7515:16 #7 0x563c6ba70311 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1167:8 #8 0x563c6bab87dc in R_execClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2389:39 #9 0x563c6bab79a1 in applyClosure_core /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2302:16 #10 0x563c6ba70d36 in Rf_applyClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2324:16 #11 0x563c6ba70d36 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1280:12 #12 0x563c6bac9e45 in do_set /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:3581:8 #13 0x563c6ba70850 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1232:12 #14 0x563c6bb408a1 in Rf_ReplIteration /data/gannet/ripley/R/svn/R-devel/src/main/main.c:264:23 #15 0x563c6bb430d0 in R_ReplConsole /data/gannet/ripley/R/svn/R-devel/src/main/main.c:317:11 #16 0x563c6bb430d0 in run_Rmainloop /data/gannet/ripley/R/svn/R-devel/src/main/main.c:1235:5 #17 0x563c6bb43162 in Rf_mainloop /data/gannet/ripley/R/svn/R-devel/src/main/main.c:1242:5 #18 0x563c6b846d3c in main /data/gannet/ripley/R/svn/R-devel/src/main/Rmain.c:29:5 #19 0x7fc1b5012574 in __libc_start_call_main (/lib64/libc.so.6+0x3574) (BuildId: 92b5376d35bb29c098175948cf3e7cbcae3aeae1) #20 0x7fc1b5012627 in __libc_start_main@GLIBC_2.2.5 (/lib64/libc.so.6+0x3627) (BuildId: 92b5376d35bb29c098175948cf3e7cbcae3aeae1) #21 0x563c6b75e7d4 in _start (/data/gannet/ripley/R/clang-ASAN/bin/exec/R+0x17d4) Address 0x7bc1b09a3521 is located in stack of thread T0 at offset 289 in frame #0 0x7bc19da2ee1f in siena::getChangeContributionsList(siena::Chain const&, SEXPREC*) /data/gannet/ripley/R/packages/tests-clang-ASAN/RSiena/src/siena07utilities.cpp:850 This frame has 20 object(s): [32, 36) 'netTypeCol' (line 856) [48, 52) 'nameCol' (line 857) [64, 68) 'effectCol' (line 858) [80, 84) 'parmCol' (line 859) [96, 100) 'int1Col' (line 860) [112, 116) 'int2Col' (line 861) [128, 132) 'initValCol' (line 862) [144, 148) 'typeCol' (line 863) [160, 164) 'groupCol' (line 864) [176, 180) 'periodCol' (line 865) [192, 196) 'pointerCol' (line 866) [208, 212) 'rateTypeCol' (line 867) [224, 228) 'intptr1Col' (line 868) [240, 244) 'intptr2Col' (line 869) [256, 260) 'intptr3Col' (line 870) [272, 276) 'settingCol' (line 871) [288, 312) 'ref.tmp' (line 898) <== Memory access at offset 289 is inside this variable [352, 376) 'ref.tmp' (line 903) [416, 440) 'ref.tmp' (line 956) [480, 504) 'values' (line 958) HINT: this may be a false positive if your program uses some custom stack unwind mechanism, swapcontext or vfork (longjmp and C++ exceptions *are* supported) SUMMARY: AddressSanitizer: stack-use-after-scope /data/gannet/ripley/R/packages/tests-clang-ASAN/RSiena/src/siena07utilities.cpp:909:9 in siena::getChangeContributionsList(siena::Chain const&, SEXPREC*) Shadow bytes around the buggy address: 0x7bc1b09a3280: f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 0x7bc1b09a3300: f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 0x7bc1b09a3380: f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 f5 0x7bc1b09a3400: f1 f1 f1 f1 04 f2 04 f2 04 f2 04 f2 04 f2 04 f2 0x7bc1b09a3480: 04 f2 04 f2 04 f2 04 f2 04 f2 04 f2 04 f2 04 f2 =>0x7bc1b09a3500: 04 f2 04 f2[f8]f8 f8 f2 f2 f2 f2 f2 f8 f8 f8 f2 0x7bc1b09a3580: f2 f2 f2 f2 f8 f8 f8 f2 f2 f2 f2 f2 f8 f8 f8 f3 0x7bc1b09a3600: f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 0x7bc1b09a3680: f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 0x7bc1b09a3700: f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 0x7bc1b09a3780: f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 f3 Shadow byte legend (one shadow byte represents 8 application bytes): Addressable: 00 Partially addressable: 01 02 03 04 05 06 07 Heap left redzone: fa Freed heap region: fd Stack left redzone: f1 Stack mid redzone: f2 Stack right redzone: f3 Stack after return: f5 Stack use after scope: f8 Global redzone: f9 Global init order: f6 Poisoned by user: f7 Container overflow: fc Array cookie: ac Intra object redzone: bb ASan internal: fe Left alloca redzone: ca Right alloca redzone: cb ==2006122==ABORTING