R Under development (unstable) (2026-01-06 r89280) -- "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 <- "pense"
> source(file.path(R.home("share"), "R", "examples-header.R"))
> options(warn = 1)
> library('pense')
Loading required package: Matrix
> 
> base::assign(".oldSearch", base::search(), pos = 'CheckExEnv')
> base::assign(".old_wd", base::getwd(), pos = 'CheckExEnv')
> cleanEx()
> nameEx("coef.pense_cvfit")
> ### * coef.pense_cvfit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: coef.pense_cvfit
> ### Title: Extract Coefficient Estimates
> ### Aliases: coef.pense_cvfit
> 
> ### ** Examples
> 
> # Compute the PENSE regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- pense(x, freeny$y, alpha = 0.5)
/data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/Mat_meat.hpp:7478:26: runtime error: reference binding to null pointer of type 'const double'
    #0 0x7b0183cb5b8c in arma::Mat<double>::colptr(unsigned int) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/Mat_meat.hpp:7478
    #1 0x7b0183cb5b8c in arma::subview<double>::extract(arma::Mat<double>&, arma::subview<double> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/subview_meat.hpp:1648
    #2 0x7b01843fa34e in arma::quasi_unwrap<arma::subview<double> >::quasi_unwrap(arma::subview<double> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/unwrap.hpp:362
    #3 0x7b01843fa34e in void arma::glue_join_cols::apply<arma::subview<double>, arma::subview<double> >(arma::Mat_noalias<arma::subview<double>::elem_type>&, arma::Glue<arma::subview<double>, arma::subview<double>, arma::glue_join_cols> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/glue_join_meat.hpp:91
    #4 0x7b01843fa34e in arma::Mat<double>::Mat<arma::subview<double>, arma::subview<double>, arma::glue_join_cols>(arma::Glue<arma::subview<double>, arma::subview<double>, arma::glue_join_cols> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/Mat_meat.hpp:6240
    #5 0x7b01843fa34e in nsoptim::PredictorResponseData::RemoveObservation(unsigned int) const nsoptim/objective/../container/data.hpp:62
    #6 0x7b01845493ba in std::forward_list<pense::enpy_psc_internal::LooStatus, std::allocator<pense::enpy_psc_internal::LooStatus> > pense::enpy_psc_internal::ComputeLoo<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(nsoptim::LsRegressionLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, unsigned int, unsigned int, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >*, std::forward_list<arma::Mat<double>, std::allocator<arma::Mat<double> > >*) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_psc.hpp:139
    #7 0x7b018447cce3 in std::forward_list<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::enpy_psc_internal::ComputePscs<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, void>(nsoptim::LsRegressionLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_psc.hpp:357
    #8 0x7b01844579fc in std::forward_list<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::PrincipalSensitiviyComponents<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(nsoptim::LsRegressionLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > const&, int) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_psc.hpp:439
    #9 0x7b01844579fc in std::forward_list<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::enpy_initest_internal::ComputeENPY<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(pense::SLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > const&, pense::enpy_initest_internal::PyConfiguration const&) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_initest.hpp:217
    #10 0x7b018440f4bf in std::forward_list<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::PenaYohaiInitialEstimators<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(pense::SLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > const&, Rcpp::Vector<19, Rcpp::PreserveStorage> const&) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_initest.hpp:464
    #11 0x7b018493e2e6 in EnpyInitialEstimatesImpl<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:183
    #12 0x7b018493e2e6 in std::forward_list<std::forward_list<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients, std::allocator<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients> >, std::allocator<std::forward_list<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients, std::allocator<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients> > > > (anonymous namespace)::EnpyInitialEstimates<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(pense::SLoss const&, std::forward_list<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, SEXPREC*, SEXPREC*, SEXPREC*, Rcpp::Vector<19, Rcpp::PreserveStorage> const&, nsoptim::_metrics_internal::Metrics<0>*) [clone .isra.0] /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:230
    #13 0x7b01848f9d20 in PenseRegressionImpl<nsoptim::MMOptimizer<pense::SLoss, nsoptim::EnPenalty, nsoptim::AugmentedLarsOptimizer<nsoptim::WeightedLsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, nsoptim::RegressionCoefficients<arma::Col<double> > > > /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:271
    #14 0x7b01848552b1 in PenseMMPenaltyImpl<nsoptim::AugmentedLarsOptimizer<nsoptim::WeightedLsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, nsoptim::EnPenalty> /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:370
    #15 0x7b01848552b1 in PenseMMDispatch<nsoptim::EnPenalty> /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:428
    #16 0x7b01847ff158 in PensePenaltyDispatch<nsoptim::EnPenalty> /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:503
    #17 0x7b01847ff158 in pense::r_interface::PenseEnRegression(SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:560
    #18 0x00000074f120 in R_doDotCall /data/gannet/ripley/R/svn/R-devel/src/main/dotcode.c:775
    #19 0x0000008e55aa in bcEval_loop /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:8682
    #20 0x0000008bbdeb in bcEval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:7515
    #21 0x00000085c642 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1167
    #22 0x00000087238a in R_execClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2389
    #23 0x00000087644a in applyClosure_core /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2302
    #24 0x000000877d67 in Rf_applyClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2324
    #25 0x000000877d67 in R_forceAndCall /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2456
    #26 0x000000a1829e in do_mapply /data/gannet/ripley/R/svn/R-devel/src/main/mapply.c:113
    #27 0x0000008ceba2 in bcEval_loop /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:8132
    #28 0x0000008bbdeb in bcEval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:7515
    #29 0x00000085c642 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1167
    #30 0x00000087238a in R_execClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2389
    #31 0x00000087644a in applyClosure_core /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2302
    #32 0x00000085cce3 in Rf_applyClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2324
    #33 0x00000085cce3 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1280
    #34 0x00000088abfe in do_set /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:3581
    #35 0x00000085d106 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1232
    #36 0x000000a02488 in Rf_ReplIteration /data/gannet/ripley/R/svn/R-devel/src/main/main.c:264
    #37 0x000000a02488 in R_ReplConsole /data/gannet/ripley/R/svn/R-devel/src/main/main.c:317
    #38 0x000000a1056a in run_Rmainloop /data/gannet/ripley/R/svn/R-devel/src/main/main.c:1235
    #39 0x000000a10602 in Rf_mainloop /data/gannet/ripley/R/svn/R-devel/src/main/main.c:1242
    #40 0x0000004131bf in main /data/gannet/ripley/R/svn/R-devel/src/main/Rmain.c:29
    #41 0x7f01a1e115f4 in __libc_start_call_main (/lib64/libc.so.6+0x35f4) (BuildId: a1dda014206b55b07f58fe8db80121b752dc3d03)
    #42 0x7f01a1e116a7 in __libc_start_main@@GLIBC_2.34 (/lib64/libc.so.6+0x36a7) (BuildId: a1dda014206b55b07f58fe8db80121b752dc3d03)
    #43 0x000000413ba4 in _start (/data/gannet/ripley/R/gcc-SAN3/bin/exec/R+0x413ba4) (BuildId: 0c03d4154a5b678104cbaeb4a17a1709e99fc88d)

/data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/access.hpp:26:100: runtime error: reference binding to null pointer of type 'double'
    #0 0x7b0183cb59fc in double& arma::access::rw<double>(double const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/access.hpp:26
    #1 0x7b0183cb59fc in arma::Mat<double>::colptr(unsigned int) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/Mat_meat.hpp:7478
    #2 0x7b0183cb59fc in arma::subview<double>::extract(arma::Mat<double>&, arma::subview<double> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/subview_meat.hpp:1648
    #3 0x7b01843fa34e in arma::quasi_unwrap<arma::subview<double> >::quasi_unwrap(arma::subview<double> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/unwrap.hpp:362
    #4 0x7b01843fa34e in void arma::glue_join_cols::apply<arma::subview<double>, arma::subview<double> >(arma::Mat_noalias<arma::subview<double>::elem_type>&, arma::Glue<arma::subview<double>, arma::subview<double>, arma::glue_join_cols> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/glue_join_meat.hpp:91
    #5 0x7b01843fa34e in arma::Mat<double>::Mat<arma::subview<double>, arma::subview<double>, arma::glue_join_cols>(arma::Glue<arma::subview<double>, arma::subview<double>, arma::glue_join_cols> const&) /data/gannet/ripley/R/test-dev/RcppArmadillo/include/current/armadillo_bits/Mat_meat.hpp:6240
    #6 0x7b01843fa34e in nsoptim::PredictorResponseData::RemoveObservation(unsigned int) const nsoptim/objective/../container/data.hpp:62
    #7 0x7b01845493ba in std::forward_list<pense::enpy_psc_internal::LooStatus, std::allocator<pense::enpy_psc_internal::LooStatus> > pense::enpy_psc_internal::ComputeLoo<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(nsoptim::LsRegressionLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, unsigned int, unsigned int, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >*, std::forward_list<arma::Mat<double>, std::allocator<arma::Mat<double> > >*) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_psc.hpp:139
    #8 0x7b018447cce3 in std::forward_list<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::enpy_psc_internal::ComputePscs<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, void>(nsoptim::LsRegressionLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_psc.hpp:357
    #9 0x7b01844579fc in std::forward_list<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PscResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::PrincipalSensitiviyComponents<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(nsoptim::LsRegressionLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > const&, int) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_psc.hpp:439
    #10 0x7b01844579fc in std::forward_list<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::enpy_initest_internal::ComputeENPY<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(pense::SLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > const&, pense::enpy_initest_internal::PyConfiguration const&) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_initest.hpp:217
    #11 0x7b018440f4bf in std::forward_list<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >, std::allocator<pense::PyResult<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > > > pense::PenaYohaiInitialEstimators<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(pense::SLoss const&, std::forward_list<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > const&, Rcpp::Vector<19, Rcpp::PreserveStorage> const&) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/enpy_initest.hpp:464
    #12 0x7b018493e2e6 in EnpyInitialEstimatesImpl<nsoptim::AugmentedLarsOptimizer<nsoptim::LsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > > /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:183
    #13 0x7b018493e2e6 in std::forward_list<std::forward_list<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients, std::allocator<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients> >, std::allocator<std::forward_list<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients, std::allocator<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::Coefficients> > > > (anonymous namespace)::EnpyInitialEstimates<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > > >(pense::SLoss const&, std::forward_list<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction, std::allocator<pense::CDPense<nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >::PenaltyFunction> > const&, SEXPREC*, SEXPREC*, SEXPREC*, Rcpp::Vector<19, Rcpp::PreserveStorage> const&, nsoptim::_metrics_internal::Metrics<0>*) [clone .isra.0] /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:230
    #14 0x7b01848f9d20 in PenseRegressionImpl<nsoptim::MMOptimizer<pense::SLoss, nsoptim::EnPenalty, nsoptim::AugmentedLarsOptimizer<nsoptim::WeightedLsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, nsoptim::RegressionCoefficients<arma::Col<double> > > > /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:271
    #15 0x7b01848552b1 in PenseMMPenaltyImpl<nsoptim::AugmentedLarsOptimizer<nsoptim::WeightedLsRegressionLoss, nsoptim::EnPenalty, nsoptim::RegressionCoefficients<arma::Col<double> > >, nsoptim::EnPenalty> /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:370
    #16 0x7b01848552b1 in PenseMMDispatch<nsoptim::EnPenalty> /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:428
    #17 0x7b01847ff158 in PensePenaltyDispatch<nsoptim::EnPenalty> /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:503
    #18 0x7b01847ff158 in pense::r_interface::PenseEnRegression(SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*, SEXPREC*) /data/gannet/ripley/R/packages/tests-gcc-SAN/pense/src/r_pense_regression.cc:560
    #19 0x00000074f120 in R_doDotCall /data/gannet/ripley/R/svn/R-devel/src/main/dotcode.c:775
    #20 0x0000008e55aa in bcEval_loop /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:8682
    #21 0x0000008bbdeb in bcEval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:7515
    #22 0x00000085c642 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1167
    #23 0x00000087238a in R_execClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2389
    #24 0x00000087644a in applyClosure_core /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2302
    #25 0x000000877d67 in Rf_applyClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2324
    #26 0x000000877d67 in R_forceAndCall /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2456
    #27 0x000000a1829e in do_mapply /data/gannet/ripley/R/svn/R-devel/src/main/mapply.c:113
    #28 0x0000008ceba2 in bcEval_loop /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:8132
    #29 0x0000008bbdeb in bcEval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:7515
    #30 0x00000085c642 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1167
    #31 0x00000087238a in R_execClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2389
    #32 0x00000087644a in applyClosure_core /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2302
    #33 0x00000085cce3 in Rf_applyClosure /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:2324
    #34 0x00000085cce3 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1280
    #35 0x00000088abfe in do_set /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:3581
    #36 0x00000085d106 in Rf_eval /data/gannet/ripley/R/svn/R-devel/src/main/eval.c:1232
    #37 0x000000a02488 in Rf_ReplIteration /data/gannet/ripley/R/svn/R-devel/src/main/main.c:264
    #38 0x000000a02488 in R_ReplConsole /data/gannet/ripley/R/svn/R-devel/src/main/main.c:317
    #39 0x000000a1056a in run_Rmainloop /data/gannet/ripley/R/svn/R-devel/src/main/main.c:1235
    #40 0x000000a10602 in Rf_mainloop /data/gannet/ripley/R/svn/R-devel/src/main/main.c:1242
    #41 0x0000004131bf in main /data/gannet/ripley/R/svn/R-devel/src/main/Rmain.c:29
    #42 0x7f01a1e115f4 in __libc_start_call_main (/lib64/libc.so.6+0x35f4) (BuildId: a1dda014206b55b07f58fe8db80121b752dc3d03)
    #43 0x7f01a1e116a7 in __libc_start_main@@GLIBC_2.34 (/lib64/libc.so.6+0x36a7) (BuildId: a1dda014206b55b07f58fe8db80121b752dc3d03)
    #44 0x000000413ba4 in _start (/data/gannet/ripley/R/gcc-SAN3/bin/exec/R+0x413ba4) (BuildId: 0c03d4154a5b678104cbaeb4a17a1709e99fc88d)

> plot(regpath)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[40]])
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4)
> plot(cv_results, se_mult = 1)
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> coef(cv_results, lambda = '1-se')
          (Intercept) lag.quarterly.revenue           price.index 
           -7.8652589             0.2141280            -0.7053433 
         income.level      market.potential 
            0.7126978             1.0754335 
> 
> 
> 
> cleanEx()
> nameEx("coef.pense_fit")
> ### * coef.pense_fit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: coef.pense_fit
> ### Title: Extract Coefficient Estimates
> ### Aliases: coef.pense_fit
> 
> ### ** Examples
> 
> # Compute the PENSE regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- pense(x, freeny$y, alpha = 0.5)
> plot(regpath)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[40]])
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4)
> plot(cv_results, se_mult = 1)
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> coef(cv_results, lambda = '1-se')
          (Intercept) lag.quarterly.revenue           price.index 
           -7.8652589             0.2141280            -0.7053433 
         income.level      market.potential 
            0.7126978             1.0754335 
> 
> 
> 
> cleanEx()
> nameEx("elnet")
> ### * elnet
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: elnet
> ### Title: Compute the Least Squares (Adaptive) Elastic Net Regularization
> ###   Path
> ### Aliases: elnet adaelnet adaen
> 
> ### ** Examples
> 
> # Compute the LS-EN regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- elnet(x, freeny$y, alpha = c(0.5, 0.75))
> plot(regpath)
> plot(regpath, alpha = 0.75)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[5]],
+      alpha = 0.75)
          (Intercept) lag.quarterly.revenue           price.index 
             9.306304              0.000000              0.000000 
         income.level      market.potential 
             0.000000              0.000000 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- elnet_cv(x, freeny$y, alpha = c(0.5, 0.75),
+                        cv_repl = 10, cv_k = 4,
+                        cv_measure = "tau")
> plot(cv_results, se_mult = 1.5)
> plot(cv_results, se_mult = 1.5, what = "coef.path")
> 
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> summary(cv_results)
EN fit with prediction performance estimated by replications of 4-fold 
cross-validation.

4 out of 4 predictors have non-zero coefficients:

                        Estimate
(Intercept)           -9.6491805
lag.quarterly.revenue  0.1899399
price.index           -0.6858733
income.level           0.7075924
market.potential       1.2247539
---

Hyper-parameters: lambda=0.003787891, alpha=0.5
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -9.6491805             0.1899399            -0.6858733 
         income.level      market.potential 
            0.7075924             1.2247539 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> summary(cv_results, lambda = "1.5-se")
EN fit with prediction performance estimated by replications of 4-fold 
cross-validation.

4 out of 4 predictors have non-zero coefficients:

                        Estimate
(Intercept)           -9.5875726
lag.quarterly.revenue  0.2270959
price.index           -0.6216322
income.level           0.6519060
market.potential       1.1972788
---

Hyper-parameters: lambda=0.01303176, alpha=0.5
> coef(cv_results, lambda = "1.5-se")
          (Intercept) lag.quarterly.revenue           price.index 
           -9.5875726             0.2270959            -0.6216322 
         income.level      market.potential 
            0.6519060             1.1972788 
> 
> 
> 
> cleanEx()
> nameEx("elnet_cv")
> ### * elnet_cv
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: elnet_cv
> ### Title: Cross-validation for Least-Squares (Adaptive) Elastic Net
> ###   Estimates
> ### Aliases: elnet_cv
> 
> ### ** Examples
> 
> # Compute the LS-EN regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- elnet(x, freeny$y, alpha = c(0.5, 0.75))
> plot(regpath)
> plot(regpath, alpha = 0.75)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[5]],
+      alpha = 0.75)
          (Intercept) lag.quarterly.revenue           price.index 
             9.306304              0.000000              0.000000 
         income.level      market.potential 
             0.000000              0.000000 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- elnet_cv(x, freeny$y, alpha = c(0.5, 0.75),
+                        cv_repl = 10, cv_k = 4,
+                        cv_measure = "tau")
> plot(cv_results, se_mult = 1.5)
> plot(cv_results, se_mult = 1.5, what = "coef.path")
> 
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> summary(cv_results)
EN fit with prediction performance estimated by replications of 4-fold 
cross-validation.

4 out of 4 predictors have non-zero coefficients:

                        Estimate
(Intercept)           -9.6491805
lag.quarterly.revenue  0.1899399
price.index           -0.6858733
income.level           0.7075924
market.potential       1.2247539
---

Hyper-parameters: lambda=0.003787891, alpha=0.5
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -9.6491805             0.1899399            -0.6858733 
         income.level      market.potential 
            0.7075924             1.2247539 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> summary(cv_results, lambda = "1.5-se")
EN fit with prediction performance estimated by replications of 4-fold 
cross-validation.

4 out of 4 predictors have non-zero coefficients:

                        Estimate
(Intercept)           -9.5875726
lag.quarterly.revenue  0.2270959
price.index           -0.6216322
income.level           0.6519060
market.potential       1.1972788
---

Hyper-parameters: lambda=0.01303176, alpha=0.5
> coef(cv_results, lambda = "1.5-se")
          (Intercept) lag.quarterly.revenue           price.index 
           -9.5875726             0.2270959            -0.6216322 
         income.level      market.potential 
            0.6519060             1.1972788 
> 
> 
> 
> cleanEx()
> nameEx("pense")
> ### * pense
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: pense
> ### Title: Compute (Adaptive) Elastic Net S-Estimates of Regression
> ### Aliases: pense adapense
> 
> ### ** Examples
> 
> # Compute the PENSE regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- pense(x, freeny$y, alpha = 0.5)
> plot(regpath)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[40]])
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4)
> plot(cv_results, se_mult = 1)
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> coef(cv_results, lambda = '1-se')
          (Intercept) lag.quarterly.revenue           price.index 
           -7.8652589             0.2141280            -0.7053433 
         income.level      market.potential 
            0.7126978             1.0754335 
> 
> 
> 
> cleanEx()
> nameEx("pense_cv")
> ### * pense_cv
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: pense_cv
> ### Title: Cross-validation for (Adaptive) PENSE Estimates
> ### Aliases: pense_cv adapense_cv
> 
> ### ** Examples
> 
> # Compute the adaptive PENSE regularization path for Freeny's
> # revenue data (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> ## Either use the convenience function directly ...
> set.seed(123)
> ada_convenience <- adapense_cv(x, freeny$y, alpha = 0.5,
+                                cv_repl = 2, cv_k = 4)
> 
> ## ... or compute the steps manually:
> # Step 1: Compute preliminary estimates with CV
> set.seed(123)
> preliminary_estimate <- pense_cv(x, freeny$y, alpha = 0,
+                                  cv_repl = 2, cv_k = 4)
> plot(preliminary_estimate, se_mult = 1)
> 
> # Step 2: Use the coefficients with best prediction performance
> # to define the penalty loadings:
> prelim_coefs <- coef(preliminary_estimate, lambda = 'min')
> pen_loadings <- 1 / abs(prelim_coefs[-1])
> 
> # Step 3: Compute the adaptive PENSE estimates and estimate
> # their prediction performance.
> set.seed(123)
> ada_manual <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4,
+                        penalty_loadings = pen_loadings)
> 
> # Visualize the prediction performance and coefficient path of
> # the adaptive PENSE estimates (manual vs. automatic)
> def.par <- par(no.readonly = TRUE)
> layout(matrix(1:4, ncol = 2, byrow = TRUE))
> plot(ada_convenience$preliminary)
> plot(preliminary_estimate)
> plot(ada_convenience)
> plot(ada_manual)
> par(def.par)
> 
> 
> 
> graphics::par(get("par.postscript", pos = 'CheckExEnv'))
> cleanEx()
> nameEx("plot.pense_cvfit")
> ### * plot.pense_cvfit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: plot.pense_cvfit
> ### Title: Plot Method for Penalized Estimates With Cross-Validation
> ### Aliases: plot.pense_cvfit
> 
> ### ** Examples
> 
> # Compute the PENSE regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- pense(x, freeny$y, alpha = 0.5)
> plot(regpath)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[40]])
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4)
> plot(cv_results, se_mult = 1)
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> coef(cv_results, lambda = '1-se')
          (Intercept) lag.quarterly.revenue           price.index 
           -7.8652589             0.2141280            -0.7053433 
         income.level      market.potential 
            0.7126978             1.0754335 
> 
> 
> 
> cleanEx()
> nameEx("plot.pense_fit")
> ### * plot.pense_fit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: plot.pense_fit
> ### Title: Plot Method for Penalized Estimates
> ### Aliases: plot.pense_fit
> 
> ### ** Examples
> 
> # Compute the PENSE regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- pense(x, freeny$y, alpha = 0.5)
> plot(regpath)
> 
> # Extract the coefficients at a certain penalization level
> coef(regpath, lambda = regpath$lambda[[1]][[40]])
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> 
> # What penalization level leads to good prediction performance?
> set.seed(123)
> cv_results <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4)
> plot(cv_results, se_mult = 1)
> 
> # Extract the coefficients at the penalization level with
> # smallest prediction error ...
> coef(cv_results)
          (Intercept) lag.quarterly.revenue           price.index 
           -7.9064997             0.2125014            -0.7070107 
         income.level      market.potential 
            0.7141099             1.0796662 
> # ... or at the penalization level with prediction error
> # statistically indistinguishable from the minimum.
> coef(cv_results, lambda = '1-se')
          (Intercept) lag.quarterly.revenue           price.index 
           -7.8652589             0.2141280            -0.7053433 
         income.level      market.potential 
            0.7126978             1.0754335 
> 
> 
> 
> cleanEx()
> nameEx("predict.pense_cvfit")
> ### * predict.pense_cvfit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: predict.pense_cvfit
> ### Title: Predict Method for PENSE Fits
> ### Aliases: predict.pense_cvfit
> 
> ### ** Examples
> 
> # Compute the LS-EN regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- elnet(x, freeny$y, alpha = 0.75)
> 
> # Predict the response using a specific penalization level
> predict(regpath, newdata = freeny[1:5, 2:5],
+         lambda = regpath$lambda[[1]][[10]])
 1962.25   1962.5  1962.75     1963  1963.25 
9.071638 9.075877 9.082341 9.091051 9.103643 
> 
> # Extract the residuals at a certain penalization level
> residuals(regpath, lambda = regpath$lambda[[1]][[5]])
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.396169224 -0.398919454 -0.378220695
1963 -0.384593892 -0.294338479 -0.278030430 -0.259140970
1964 -0.265543684 -0.219857551 -0.206023748 -0.173545125
1965 -0.192086388 -0.146253918 -0.133786817 -0.096671191
1966 -0.090347926 -0.044601264 -0.027307275 -0.015531362
1967  0.006739697  0.037235389  0.038869333  0.071407419
1968  0.086275062  0.102036759  0.141643505  0.167310507
1969  0.175437660  0.211500792  0.222942549  0.260029329
1970  0.247870647  0.296181577  0.294470169  0.278217170
1971  0.306686546  0.334684047  0.353729154  0.367702082
> 
> # Select penalization level via cross-validation
> set.seed(123)
> cv_results <- elnet_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 10, cv_k = 4)
> 
> # Predict the response using the "best" penalization level
> predict(cv_results, newdata = freeny[1:5, 2:5])
 1962.25   1962.5  1962.75     1963  1963.25 
8.795162 8.807070 8.824535 8.842175 8.882970 
> 
> # Extract the residuals at the "best" penalization level
> residuals(cv_results)
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.002801588 -0.015699794 -0.009674689
1963 -0.029165027  0.024539756  0.012794692  0.013400637
1964 -0.014177641  0.006727561 -0.001786569  0.012847301
1965 -0.026214283 -0.003738367 -0.010414370 -0.002497682
1966 -0.014953173  0.014923561  0.008857587  0.002955549
1967 -0.002438578  0.011336771 -0.004817002 -0.002203485
1968 -0.014622332 -0.016038521  0.004783442  0.009509723
1969  0.008935501  0.025135859  0.011008309  0.028171208
1970 -0.021812388  0.015300404 -0.005936032 -0.018484409
1971 -0.011338929  0.005850584  0.003783641  0.007952774
> # Extract the residuals at a more parsimonious penalization level
> residuals(cv_results, lambda = "1.5-se")
              Qtr1          Qtr2          Qtr3          Qtr4
1962               -0.0133914763 -0.0253025812 -0.0180073467
1963 -0.0375085950  0.0197904960  0.0063674275  0.0071084444
1964 -0.0199445085  0.0028559476 -0.0059886764  0.0089958759
1965 -0.0300906249 -0.0052788324 -0.0128420949 -0.0036364879
1966 -0.0166186511  0.0137904162  0.0073750895  0.0016121587
1967 -0.0021618673  0.0116385091 -0.0046227113  0.0002016235
1968 -0.0117185912 -0.0127504673  0.0088610048  0.0131305182
1969  0.0114094522  0.0285319822  0.0147126545  0.0325247699
1970 -0.0158575338  0.0222103711  0.0004937030 -0.0127802705
1971 -0.0035765461  0.0133307584  0.0117139290  0.0154227310
> 
> 
> 
> cleanEx()
> nameEx("predict.pense_fit")
> ### * predict.pense_fit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: predict.pense_fit
> ### Title: Predict Method for PENSE Fits
> ### Aliases: predict.pense_fit
> 
> ### ** Examples
> 
> # Compute the LS-EN regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- elnet(x, freeny$y, alpha = 0.75)
> 
> # Predict the response using a specific penalization level
> predict(regpath, newdata = freeny[1:5, 2:5],
+         lambda = regpath$lambda[[1]][[10]])
 1962.25   1962.5  1962.75     1963  1963.25 
9.071638 9.075877 9.082341 9.091051 9.103643 
> 
> # Extract the residuals at a certain penalization level
> residuals(regpath, lambda = regpath$lambda[[1]][[5]])
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.396169224 -0.398919454 -0.378220695
1963 -0.384593892 -0.294338479 -0.278030430 -0.259140970
1964 -0.265543684 -0.219857551 -0.206023748 -0.173545125
1965 -0.192086388 -0.146253918 -0.133786817 -0.096671191
1966 -0.090347926 -0.044601264 -0.027307275 -0.015531362
1967  0.006739697  0.037235389  0.038869333  0.071407419
1968  0.086275062  0.102036759  0.141643505  0.167310507
1969  0.175437660  0.211500792  0.222942549  0.260029329
1970  0.247870647  0.296181577  0.294470169  0.278217170
1971  0.306686546  0.334684047  0.353729154  0.367702082
> 
> # Select penalization level via cross-validation
> set.seed(123)
> cv_results <- elnet_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 10, cv_k = 4)
> 
> # Predict the response using the "best" penalization level
> predict(cv_results, newdata = freeny[1:5, 2:5])
 1962.25   1962.5  1962.75     1963  1963.25 
8.795162 8.807070 8.824535 8.842175 8.882970 
> 
> # Extract the residuals at the "best" penalization level
> residuals(cv_results)
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.002801588 -0.015699794 -0.009674689
1963 -0.029165027  0.024539756  0.012794692  0.013400637
1964 -0.014177641  0.006727561 -0.001786569  0.012847301
1965 -0.026214283 -0.003738367 -0.010414370 -0.002497682
1966 -0.014953173  0.014923561  0.008857587  0.002955549
1967 -0.002438578  0.011336771 -0.004817002 -0.002203485
1968 -0.014622332 -0.016038521  0.004783442  0.009509723
1969  0.008935501  0.025135859  0.011008309  0.028171208
1970 -0.021812388  0.015300404 -0.005936032 -0.018484409
1971 -0.011338929  0.005850584  0.003783641  0.007952774
> # Extract the residuals at a more parsimonious penalization level
> residuals(cv_results, lambda = "1.5-se")
              Qtr1          Qtr2          Qtr3          Qtr4
1962               -0.0133914763 -0.0253025812 -0.0180073467
1963 -0.0375085950  0.0197904960  0.0063674275  0.0071084444
1964 -0.0199445085  0.0028559476 -0.0059886764  0.0089958759
1965 -0.0300906249 -0.0052788324 -0.0128420949 -0.0036364879
1966 -0.0166186511  0.0137904162  0.0073750895  0.0016121587
1967 -0.0021618673  0.0116385091 -0.0046227113  0.0002016235
1968 -0.0117185912 -0.0127504673  0.0088610048  0.0131305182
1969  0.0114094522  0.0285319822  0.0147126545  0.0325247699
1970 -0.0158575338  0.0222103711  0.0004937030 -0.0127802705
1971 -0.0035765461  0.0133307584  0.0117139290  0.0154227310
> 
> 
> 
> cleanEx()
> nameEx("regmest_cv")
> ### * regmest_cv
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: regmest_cv
> ### Title: Cross-validation for (Adaptive) Elastic Net M-Estimates
> ### Aliases: regmest_cv adamest_cv
> 
> ### ** Examples
> 
> # Compute the adaptive PENSE regularization path for Freeny's
> # revenue data (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> ## Either use the convenience function directly ...
> set.seed(123)
> ada_convenience <- adapense_cv(x, freeny$y, alpha = 0.5,
+                                cv_repl = 2, cv_k = 4)
> 
> ## ... or compute the steps manually:
> # Step 1: Compute preliminary estimates with CV
> set.seed(123)
> preliminary_estimate <- pense_cv(x, freeny$y, alpha = 0,
+                                  cv_repl = 2, cv_k = 4)
> plot(preliminary_estimate, se_mult = 1)
> 
> # Step 2: Use the coefficients with best prediction performance
> # to define the penalty loadings:
> prelim_coefs <- coef(preliminary_estimate, lambda = 'min')
> pen_loadings <- 1 / abs(prelim_coefs[-1])
> 
> # Step 3: Compute the adaptive PENSE estimates and estimate
> # their prediction performance.
> set.seed(123)
> ada_manual <- pense_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 2, cv_k = 4,
+                        penalty_loadings = pen_loadings)
> 
> # Visualize the prediction performance and coefficient path of
> # the adaptive PENSE estimates (manual vs. automatic)
> def.par <- par(no.readonly = TRUE)
> layout(matrix(1:4, ncol = 2, byrow = TRUE))
> plot(ada_convenience$preliminary)
> plot(preliminary_estimate)
> plot(ada_convenience)
> plot(ada_manual)
> par(def.par)
> 
> 
> 
> graphics::par(get("par.postscript", pos = 'CheckExEnv'))
> cleanEx()
> nameEx("residuals.pense_cvfit")
> ### * residuals.pense_cvfit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: residuals.pense_cvfit
> ### Title: Extract Residuals
> ### Aliases: residuals.pense_cvfit
> 
> ### ** Examples
> 
> # Compute the LS-EN regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- elnet(x, freeny$y, alpha = 0.75)
> 
> # Predict the response using a specific penalization level
> predict(regpath, newdata = freeny[1:5, 2:5],
+         lambda = regpath$lambda[[1]][[10]])
 1962.25   1962.5  1962.75     1963  1963.25 
9.071638 9.075877 9.082341 9.091051 9.103643 
> 
> # Extract the residuals at a certain penalization level
> residuals(regpath, lambda = regpath$lambda[[1]][[5]])
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.396169224 -0.398919454 -0.378220695
1963 -0.384593892 -0.294338479 -0.278030430 -0.259140970
1964 -0.265543684 -0.219857551 -0.206023748 -0.173545125
1965 -0.192086388 -0.146253918 -0.133786817 -0.096671191
1966 -0.090347926 -0.044601264 -0.027307275 -0.015531362
1967  0.006739697  0.037235389  0.038869333  0.071407419
1968  0.086275062  0.102036759  0.141643505  0.167310507
1969  0.175437660  0.211500792  0.222942549  0.260029329
1970  0.247870647  0.296181577  0.294470169  0.278217170
1971  0.306686546  0.334684047  0.353729154  0.367702082
> 
> # Select penalization level via cross-validation
> set.seed(123)
> cv_results <- elnet_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 10, cv_k = 4)
> 
> # Predict the response using the "best" penalization level
> predict(cv_results, newdata = freeny[1:5, 2:5])
 1962.25   1962.5  1962.75     1963  1963.25 
8.795162 8.807070 8.824535 8.842175 8.882970 
> 
> # Extract the residuals at the "best" penalization level
> residuals(cv_results)
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.002801588 -0.015699794 -0.009674689
1963 -0.029165027  0.024539756  0.012794692  0.013400637
1964 -0.014177641  0.006727561 -0.001786569  0.012847301
1965 -0.026214283 -0.003738367 -0.010414370 -0.002497682
1966 -0.014953173  0.014923561  0.008857587  0.002955549
1967 -0.002438578  0.011336771 -0.004817002 -0.002203485
1968 -0.014622332 -0.016038521  0.004783442  0.009509723
1969  0.008935501  0.025135859  0.011008309  0.028171208
1970 -0.021812388  0.015300404 -0.005936032 -0.018484409
1971 -0.011338929  0.005850584  0.003783641  0.007952774
> # Extract the residuals at a more parsimonious penalization level
> residuals(cv_results, lambda = "1.5-se")
              Qtr1          Qtr2          Qtr3          Qtr4
1962               -0.0133914763 -0.0253025812 -0.0180073467
1963 -0.0375085950  0.0197904960  0.0063674275  0.0071084444
1964 -0.0199445085  0.0028559476 -0.0059886764  0.0089958759
1965 -0.0300906249 -0.0052788324 -0.0128420949 -0.0036364879
1966 -0.0166186511  0.0137904162  0.0073750895  0.0016121587
1967 -0.0021618673  0.0116385091 -0.0046227113  0.0002016235
1968 -0.0117185912 -0.0127504673  0.0088610048  0.0131305182
1969  0.0114094522  0.0285319822  0.0147126545  0.0325247699
1970 -0.0158575338  0.0222103711  0.0004937030 -0.0127802705
1971 -0.0035765461  0.0133307584  0.0117139290  0.0154227310
> 
> 
> 
> cleanEx()
> nameEx("residuals.pense_fit")
> ### * residuals.pense_fit
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: residuals.pense_fit
> ### Title: Extract Residuals
> ### Aliases: residuals.pense_fit
> 
> ### ** Examples
> 
> # Compute the LS-EN regularization path for Freeny's revenue data
> # (see ?freeny)
> data(freeny)
> x <- as.matrix(freeny[ , 2:5])
> 
> regpath <- elnet(x, freeny$y, alpha = 0.75)
> 
> # Predict the response using a specific penalization level
> predict(regpath, newdata = freeny[1:5, 2:5],
+         lambda = regpath$lambda[[1]][[10]])
 1962.25   1962.5  1962.75     1963  1963.25 
9.071638 9.075877 9.082341 9.091051 9.103643 
> 
> # Extract the residuals at a certain penalization level
> residuals(regpath, lambda = regpath$lambda[[1]][[5]])
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.396169224 -0.398919454 -0.378220695
1963 -0.384593892 -0.294338479 -0.278030430 -0.259140970
1964 -0.265543684 -0.219857551 -0.206023748 -0.173545125
1965 -0.192086388 -0.146253918 -0.133786817 -0.096671191
1966 -0.090347926 -0.044601264 -0.027307275 -0.015531362
1967  0.006739697  0.037235389  0.038869333  0.071407419
1968  0.086275062  0.102036759  0.141643505  0.167310507
1969  0.175437660  0.211500792  0.222942549  0.260029329
1970  0.247870647  0.296181577  0.294470169  0.278217170
1971  0.306686546  0.334684047  0.353729154  0.367702082
> 
> # Select penalization level via cross-validation
> set.seed(123)
> cv_results <- elnet_cv(x, freeny$y, alpha = 0.5,
+                        cv_repl = 10, cv_k = 4)
> 
> # Predict the response using the "best" penalization level
> predict(cv_results, newdata = freeny[1:5, 2:5])
 1962.25   1962.5  1962.75     1963  1963.25 
8.795162 8.807070 8.824535 8.842175 8.882970 
> 
> # Extract the residuals at the "best" penalization level
> residuals(cv_results)
             Qtr1         Qtr2         Qtr3         Qtr4
1962              -0.002801588 -0.015699794 -0.009674689
1963 -0.029165027  0.024539756  0.012794692  0.013400637
1964 -0.014177641  0.006727561 -0.001786569  0.012847301
1965 -0.026214283 -0.003738367 -0.010414370 -0.002497682
1966 -0.014953173  0.014923561  0.008857587  0.002955549
1967 -0.002438578  0.011336771 -0.004817002 -0.002203485
1968 -0.014622332 -0.016038521  0.004783442  0.009509723
1969  0.008935501  0.025135859  0.011008309  0.028171208
1970 -0.021812388  0.015300404 -0.005936032 -0.018484409
1971 -0.011338929  0.005850584  0.003783641  0.007952774
> # Extract the residuals at a more parsimonious penalization level
> residuals(cv_results, lambda = "1.5-se")
              Qtr1          Qtr2          Qtr3          Qtr4
1962               -0.0133914763 -0.0253025812 -0.0180073467
1963 -0.0375085950  0.0197904960  0.0063674275  0.0071084444
1964 -0.0199445085  0.0028559476 -0.0059886764  0.0089958759
1965 -0.0300906249 -0.0052788324 -0.0128420949 -0.0036364879
1966 -0.0166186511  0.0137904162  0.0073750895  0.0016121587
1967 -0.0021618673  0.0116385091 -0.0046227113  0.0002016235
1968 -0.0117185912 -0.0127504673  0.0088610048  0.0131305182
1969  0.0114094522  0.0285319822  0.0147126545  0.0325247699
1970 -0.0158575338  0.0222103711  0.0004937030 -0.0127802705
1971 -0.0035765461  0.0133307584  0.0117139290  0.0154227310
> 
> 
> 
> ### * <FOOTER>
> ###
> cleanEx()
> options(digits = 7L)
> base::cat("Time elapsed: ", proc.time() - base::get("ptime", pos = 'CheckExEnv'),"\n")
Time elapsed:  115.743 2.501 121.31 0 0 
> grDevices::dev.off()
null device 
          1 
> ###
> ### Local variables: ***
> ### mode: outline-minor ***
> ### outline-regexp: "\\(> \\)?### [*]+" ***
> ### End: ***
> quit('no')