|Date: ||Wed, 4 Oct 2006 14:17:38 -0400|
|Reply-To: ||Peter Flom <Flom@NDRI.ORG>|
|Sender: ||"SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>|
|From: ||Peter Flom <Flom@NDRI.ORG>|
|Subject: ||Re: Is a multiple regression ok under these circumstances?|
|Content-Type: ||text/plain; charset=US-ASCII|
>>> Duck-Hye Yang <dyang@CHAPINHALL.ORG> 10/4/2006 12:05 pm >>> wrote
My data has somewhat small sample size (N=79).
A variable of primary interest as an independent variable is
categorical, having three values.
1=have condition A (N=30)
2=have condition B (N=40)
3=have both A and B (N=9)
As you see, the third one has a small sample size. And there may be
multicollnearity among the three groups.
Is the use of multiple regression ok under these circumstances?
As usual, it would be nice to have some context.
Is this the only IV in the model?
What are these 'conditions'?
Does anyone have neither condition?
Is this from a survey (you KNEW David Cassell would ask, but I am on
the East Coast, so I am asking first :-))
I don't understand what you mean by collinearity in this context.
Collinearity is a relation among multiple IVs. It sounds like you have
ONE IV with three levels. But perhaps not
If you write back to SAS-L with answers to these questions, then
perhaps someone will be able to help (maybe even me).
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)