probe-package {probe}

probe: Sparse High-Dimensional Linear Regression with PROBE

Description

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. More information can be found in McLain, Zgodic, and Bondell (2022) arXiv:2209.08139.

Details

Examples for applying PROBE to sparse high-dimensional linear regression are given for one-at-a-time probe_one or all-at-once probe type optimization.

Author(s)

Maintainer: Alexander McLain [e-mail] (ORCID)

Authors:

• Anja Zodiac [contributor]

References

• McLain, A. C., Zgodic, A., & Bondell, H. (2022). Sparse high-dimensional linear regression with a partitioned empirical Bayes ECM algorithm. arXiv preprint arXiv:2209.08139.

See Also

Useful links:

• Report bugs at https://github.com/alexmclain/PROBE/issues