[R] Checking the assumptions for a proper GLM model

[David Winsemius]

At one time the "answer" would have been to buy a copy of Venables and  
Ripley's "Modern Applied Statistics with S" (and R), and that would  
still be a sensible strategy. There are now quite a few other R- 
centric texts that have been published in the last few years. Search  
Amazon if needed. You seem to be asking for a tutorial on general  
linear modeling (which if you read the Posting Guide you will find is  
not a service offered by the r-help list.)  Perhaps you should have  
edited the link you provided in the obvious fashion:

http://www.ats.ucla.edu/stat/R/

Perhaps one of these pages:
http://www.ats.ucla.edu/stat/R/dae/default.htm

The UCLA Statistics website used to be dismissive of R, but they more  
recently appear to have seen the light. There is also a great amount  
of contributed teaching material on CRAN:

http://cran.r-project.org/other-docs.html

... and more would be readily available via Googling with "r-project"  
as part of a search strategy. Frank Harrell's material is in  
particular quite useful:

http://biostat.mc.vanderbilt.edu/wiki/Main/StatComp

-- 
David.

On Feb 18, 2010, at 8:32 AM, Jay wrote:

> So what I'm looking for is readily available tools/packages that could
> produce some of the following:
>
> 3.6 Summary of Useful Commands (STATA: Source:
> http://www.ats.ucla.edu/stat/Stata/webbooks/logistic/chapter3/statalog3.htm)
>
>    * linktest--performs a link test for model specification, in our
> case to check if logit is the right link function to use. This command
> is issued after the logit or logistic command.
<snipped>
> and performs nonlinearity test.
>
> But, since I'm new to GLM, I owuld greatly appreciate how you/others
> go about and test the validity of a GLM model.
>
>
> On Feb 18, 1:18 am, Jay <josip.2... at gmail.com> wrote:
>> Hello,
>>
>> Are there any packages/functions available for testing the  
>> assumptions
>> underlying assumptions for a good GLM model? Like linktest in STATA
>> and smilar. If not, could somebody please describe their work process
>> when they check the validity of a logit/probit model?
>>
>> Regards,
>> Jay
>


David Winsemius, MD
Heritage Laboratories
West Hartford, CT