Message-ID: <1324644418363-4228495.post@n4.nabble.com>
Date: 2011-12-23T12:46:58Z
From: schell
Subject: lasso based selection for mixed model
In-Reply-To: <loom.20090507T154802-958@post.gmane.org>
Dear Dieter
There has been some effort examining Lasso-type estimators for mixed models.
It is more involved than with other type of models.
We have studied Gaussian and generalized linear mixed models including a
Lasso-type penalty for the fixed effects and we are now able to provide two
packages: lmmlasso and glmmlasso. Both are available from R-Forge (the
former even from CRAN).
Andreas Groll provides the glmmLasso package, which is available from CRAN.
Juerg Schelldorfer
--
View this message in context: http://r.789695.n4.nabble.com/lasso-based-selection-for-mixed-model-tp887308p4228495.html
Sent from the R help mailing list archive at Nabble.com.