Date: Tue, 23 Dec 2003 12:22:07 -0500
Reply-To: Peter Flom <flom@NDRI.ORG>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: Peter Flom <flom@NDRI.ORG>
Subject: Re: Stepwise Poisson Regression
Content-Type: text/plain; charset=US-ASCII
> My first thought is WHY does your research require such a thing?
David Cassell replied
>>>Don't think of that as flippant. Seriously think about that
Indeed, I did not mean it flippantly. Thinking about what analysis you
are doing is, I think it's safe to say, always a good idea. As Abraham
Lincoln said "If I had 8 hours to chop down a tree, I would spend 4 of
them sharpening my axe".
> My third thought is, if you really need to do this, and if there's
> SAS solution, then it's (relatively) simple to do it in R, which is
> free, or in S+, which is not free. The biggest difference for your
> purposes (besides cost) is that it can be tricky to get data from
> to R, although there is an R library (foreign) which helps somewhat.
>> The SAS-data-set-reading package in R is troublesome, at best. I >>
would recommend using PROC EXPORT to turn your SAS data set >> into a
flat file that R can read more easily.
I am glad I am not the only one to experience this, and that such a
highly skilled user as David shares these difficulties. I wonder if
David has any more details on PROC EXPORT to R, which I have also found
a little tricky.
I've actually resorted to using DBMS Copy to make the SAS data set into
an SPSS data set, and then using R's read.spss, which works considerably
more easily than read.sas....
Peter L. Flom, PhD
Assistant Director, Statistics and Data Analysis Core
Center for Drug Use and HIV Research
National Development and Research Institutes
71 W. 23rd St
New York, NY 10010
(212) 845-4485 (voice)
(917) 438-0894 (fax)