Package: probe 1.1

probe: Sparse High-Dimensional Linear Regression with a PaRtitiOned Empirical Bayes Ecm (PROBE) Algorithm

Implements an efficient and powerful Bayesian approach for sparse high-dimensional linear regression. It uses minimal prior assumptions on the parameters through plug-in empirical Bayes estimates of hyperparameters. An efficient Parameter-Expanded Expectation-Conditional-Maximization (PX-ECM) algorithm estimates maximum a posteriori (MAP) values of regression parameters and variable selection probabilities. The PX-ECM results in a robust computationally efficient coordinate-wise optimization, which adjusts for the impact of other predictor variables. The E-step is motivated by the popular two-group approach to multiple testing. The result is a PaRtitiOned empirical Bayes Ecm (PROBE) algorithm applied to sparse high-dimensional linear regression, implemented using one-at-a-time or all-at-once type optimization. Simulation studies found the all-at-once variant to be superior.

Authors:Alexander McLain [aut, cre], Anja Zgodic [aut, ctb]

probe_1.1.tar.gz
probe_1.1.zip(r-4.5)probe_1.1.zip(r-4.4)probe_1.1.zip(r-4.3)
probe_1.1.tgz(r-4.4-x86_64)probe_1.1.tgz(r-4.4-arm64)probe_1.1.tgz(r-4.3-x86_64)probe_1.1.tgz(r-4.3-arm64)
probe_1.1.tar.gz(r-4.5-noble)probe_1.1.tar.gz(r-4.4-noble)
probe_1.1.tgz(r-4.4-emscripten)probe_1.1.tgz(r-4.3-emscripten)
probe.pdf |probe.html✨
probe/json (API)

Peer review:

Bug tracker:https://github.com/alexmclain/probe/issues

On CRAN:

bayesian-methodshigh-dimensional-datahigh-dimensional-inferencelinear-modelsmachine-learning

3 exports 1 stars 1.18 score 11 dependencies 4 scripts 150 downloads

Last updated 1 months agofrom:b47db222e0. Checks:OK: 1 WARNING: 8. Indexed: yes.

Exports:predict_probe_funcprobeprobe_one

Dependencies:codetoolsforeachglmnetiteratorslatticeMatrixRcppRcppArmadilloRcppEigenshapesurvival