lassogrp implements the Lasso regression method for several regression types (ordinary, logistic, Poisson and user-provided models). It offers the group lasso which is suitable when factors appear in the model. It also provides a user-friendly way to perform the adaptive lasso, which consists of two calls to lasso, the second one using a weighted L1 penalization term, where the weights depend on the results of the first call.
This package replaces the grplasso package and extends its functionality.
The package includes methods for printing and plotting as well as a cross validation function and functions to extract specified fits from the lasso results.
It is in development.
Werner A. Stahel, ETH Zurich, firstname.lastname@example.org, based on code of Lukas Meier
Lukas Meier, Sara van de Geer and Peter B\"uhlmann (2008),
The Group Lasso for Logistic Regression,
Journal of the Royal Statistical Society, 70 (1), 53–71;
see also http://stat.ethz.ch/~meier/logistic-grouplasso.php