This packages computes sparse estimates for generalized linear models (GLM) via MIC, a short name for "Minimizing approxiamted Inforatmion Criterion". MIC mimics the best subset selection using a penalized likelihood approach yet with no need of a tuning parameter. The problem is further reformulated with a reparameterization step so that it reduces to an unconstrained nonconvex yet smooth programming problem, which can be solved efficiently. The global optimization algorithm, Simulated annealing (SA) or its generalized version (GenSA), is used for optimization, possibly combined with a local optimization algorithm (BFGS). Furthermore, the reparameterization tactic yields an additional advantage in terms of circumventing post-selection inference.
|Maintainer||Xiaogang Su <[email protected]l.com>|
|Package repository||View on GitHub|
Install the latest version of this package by entering the following in R:
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.