Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Charles Lindsey <clindsey@stata.com> |
To | Charles Lindsey <clindsey@stata.com>, statalist@hsphsun2.harvard.edu |
Subject | st: new package -vselect- available in SSC |
Date | Tue, 18 Mar 2014 11:52:24 -0500 |
Thanks to Kit Baum, the package -vselect- is now available in the SSC. To install, type -ssc install vselect-. -vselect- performs variable selection for linear regression. Through the use of the Furnival-Wilson leaps-and-bounds algorithm, all-subsets variable selection is supported. The stepwise methods, forward selection and backward elimination, are also supported. This version of the -vselect- package adds two features. Now when performing all-subsets regression, users may specify the number of best models to be reported at each predictor size. Also, factor variables are now supported in the -fix()- option. Reference: Lindsey C. and S. Sheather (2010), Variable Selection in Linear Regression, The Stata Journal, 10:650-669. --Charles clindsey@stata.com * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/