One correction, one comment, one suggestion:
On Wed, Dec 5, 2012 at 4:44 AM, eliza botto <eliza_botto@hotmail.com>
wrote:
>
> Dear UseRs,
>
> I wanted to know that i have been using "leaps" for the proper
models
> selection for my work. I read so many articles from internet which
> categorically outlined that "leaps" command for model selection
should
> never be used as its not efficient.
No. That is not the problem. The problem is that it efficiently produces
nonsense, as your next line indicates.
> Moreover, as a matter of fact, i personally noticed that the accuracy of
> "leaps" package is very much questionable.
>
> Is there an alternative package, which is more efficient????
>
You are asking about model selection/building, which is a central theme in
statistics. There is no simple answer to your question.
Moreover, this is not the place for such discussions. I strongly recommend
that you consult a local statistician, as you are clearly out of your
depth. Failing that, post to a statistics list like stats.stackexchange.com
.
-- Bert
>
> your help will be deeply acknowledged...!!!!
>
> warm regards
>
> eliza
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@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.
>
--
Bert Gunter
Genentech Nonclinical Biostatistics
Internal Contact Info:
Phone: 467-7374
Website:
http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm
[[alternative HTML version deleted]]