Hello, I am using the 'regsubsets' function (from leaps package) to get the best linear models to explain 1 variable from 1 to 5 explanatory variables (exhaustive search). Is there anyone who can tell me on which criterion is based the 'regsubsets' function ? Thank you. samuel Samuel BERTRAND Doctorant Laboratoire de Biomecanique LBM - ENSAM - CNRS UMR 8005 http://bio-web.paris.ensam.fr 151, bd de l'Hopital 75013 PARIS Tel. +33 (0) 1 44 24 64 53 Fax +33 (0) 1 44 24 63 66 [[alternative HTML version deleted]]
> Is there anyone who can tell me > on which criterion is based > the 'regsubsets' function ?the leaps help page says: cp or adjr2 or r2 is the value of the chosen model selection statistic for each model so each of these can be chosen as the selection statistic using the method argument hth, ingmar
> > Is there anyone who can tell me > > on which criterion is based > > the 'regsubsets' function ? > > Samuel>the leaps help page says: > >cp or adjr2 or r2 is the value of the chosen model selection statistic for >each model > >so each of these can be chosen as the selection statistic using the method >argument > >hth, ingmarIn fact, 'regsubsets' does not enable to choose among cp, adrjr2 or r2 as 'leaps' function does. Do you know the default criterion? Or do you think it means that the result would be the same for the three criteria ? Samuel BERTRAND Doctorant LBM - ENSAM - CNRS UMR 8005 http://bio-web.paris.ensam.fr [[alternative HTML version deleted]]
On Tue, 27 Sep 2005, Samuel Bertrand wrote:> Hello, > > I am using the 'regsubsets' function > (from leaps package) > to get the best linear models > to explain 1 variable > from 1 to 5 explanatory variables > (exhaustive search). > > Is there anyone who can tell me > on which criterion is based > the 'regsubsets' function ? >As you get a best model for each size, all the commonly used criteria are equivalent. RSS, AIC, BIC, Mallows Cp, adjusted R^2, etc, all give the same ordering for models with the same number of predictors. -thomas
Questions like this are best directed to the package maintainer(s).
From help(package="leaps"), I learned that Thomas Lumley is the
author
and maintainer for "leaps"; I'm including him as a 'cc',
so he can
correct or add to my comments if he feels so inclined.
After some searching, I learned that "?plot.regsubsets" includes an
argument scale=c("bic", "Cp", "adjr2",
"r2"). From this, I infer that
you have your choice of these four criteria.
hope this helps.
spencer graves
Samuel Bertrand wrote:
> Hello,
>
> I am using the 'regsubsets' function
> (from leaps package)
> to get the best linear models
> to explain 1 variable
> from 1 to 5 explanatory variables
> (exhaustive search).
>
> Is there anyone who can tell me
> on which criterion is based
> the 'regsubsets' function ?
>
> Thank you.
>
> samuel
>
>
>
>
>
> Samuel BERTRAND
> Doctorant
> Laboratoire de Biomecanique
> LBM - ENSAM - CNRS UMR 8005
> http://bio-web.paris.ensam.fr
> 151, bd de l'Hopital
> 75013 PARIS
> Tel. +33 (0) 1 44 24 64 53
> Fax +33 (0) 1 44 24 63 66
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
--
Spencer Graves, PhD
Senior Development Engineer
PDF Solutions, Inc.
333 West San Carlos Street Suite 700
San Jose, CA 95110, USA
spencer.graves at pdf.com
www.pdf.com <http://www.pdf.com>
Tel: 408-938-4420
Fax: 408-280-7915