There are at least two options.
There is the sparseLDA package that was written by the author of
"Sparse Discriminant Analysis". The paper can be found at
http://www-stat.stanford.edu/~hastie/Papers/sda_line.pdf
The initial version of the package is here:
http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=5672
I'm working on another version that is more R-centric (e.g. object
oriented, has predict methods, etc). I think that will be on CRAN
soon.
Another option is the sparse PLS model in the spls package that also
uses methods similar to the elastic net. I've written functions to
extend this to classification in the same manner as the plsda function
in the caret package. I've submitted the code to the package
maintainers, but I can send it to anyone who emails me off-list.
Max
On Tue, Dec 9, 2008 at 1:09 PM, Jack Luo <jluo.rhelp at gmail.com>
wrote:> Hi, List
>
> The elastic net package (by Hastie and Zou at Stanford) is used to do
> regularization and variable selection, it can also do regression. I am
> wondering if it can perform binary classification (discrete outcome).
> Anybody having similar experience?
>
> Many thanks,
>
> -Jack
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> 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.
>
--
Max