all subsets for glm
If you actually want to find the best subsets, you can get a good approximation by using leaps on the weighted least squares fit that is the last iteration of the IWLS algorithm for fitting the glm. Running regsubsets witha reasonably large value of nbest and then refitting the top models as glms afterwards will fairly realiably give the best glms. Whether this is better than lasso depends on what you are trying to do - IMO the only point of all-subsets regression is to get many best models rather than a single one, and lasso doesn't do at all well at that. -thomas
On Sat, 4 Apr 2009, Harald von Waldow wrote:
Of all the dangerous ways of doing this and getting confusing results, gl1ce in lasso2 should be the least risky.
Thanks Dieter. In case an exhaustive search (all subsets) remains infeasible, I'll include a shrinkage method for sure. Looks like glmpath could be useful here. Best, Harald
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Thomas Lumley Assoc. Professor, Biostatistics tlumley at u.washington.edu University of Washington, Seattle