[R] lasso for variable selection
andy_liaw at merck.com
Mon Aug 14 16:09:13 CEST 2006
For "importance" it's probably best to stick with absolute values of
coefficients, instead of value of the penalty parameter for which the
coefficients changed to non-zero.
Friedman skipped a lot of details on his rule ensemble in that talk, due to
time constraint. In his implementation he was using his own algorithm,
PathSeeker, for which paper and software are available on his web page.
PathSeeker is a different generalization of LASSO than LAR.
> Attended JSM last week and Friedman mentioned the use of
> LASSO for variable selection (he uses it for rules
> ensembles). I am an econometrician and not familiar with, i
> started running the examples in
> R this week and you get to the plots section of the LARS package.
> Plots of beta/max(beta) vs standardized coefficients. How
> does one interpret them? u see plots of each variable
> converging to zero at different times - its pretty cool - but
> can i use this for variable importance?
> for variable selection - i have a group of correlated
> variables that we need to determine importance in predicting
> change of a Y variable.
> R-help at stat.math.ethz.ch mailing list
> PLEASE do read the posting guide
> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help