[R-sig-eco] how-to identify redundant predictors

[Ivailo]

On Sat, Apr 21, 2012 at 12:02 PM, C Hess <13184 at stud.leuphana.de> wrote:
> dear list,
>
> my actual task in the process of fitting an lme()-model is to identify and
> remove redundant predictors before using them as fixed effects.
>
> to get an overview and pick a group of final predictors i use the
> correlation-coefficients cor() and a pca prcomp()
>
> trying and testing seems an essential way in the process of model fitting,
> but maybe there is another way/method to get a list of predictors in a more
> structured way like: this are the top 5 predictors with the fewest
> correlation, or something else
>
> thanks
> CH

You have not mentioned how many samples and predictor variables you
have, but I think that you can also use PLS (partial least square
regression, package "pls"), especially if you have many, possibly
correlated, predictor variables, and relatively few samples. The
accompanying web-site (http://mevik.net/work/software/pls.html)
provides R-code that implements the VIP (variance importance in
projection) algorithm that might be useful during variable selection.

Cheers,
Ivailo
-- 
UBUNTU: a person is a person through other persons.