| Date: | Wed, 8 Dec 1999 16:46:19 -0500 |
|---|
| Reply-To: | Walter Davis <walter_davis@UNC.EDU> |
|---|
| Sender: | "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU> |
|---|
| From: | Walter Davis <walter_davis@UNC.EDU> |
|---|
| Organization: | The University of North Carolina at Chapel Hill |
|---|
| Subject: | Re: confusing MIXED test results |
|---|
| Content-Type: | text/plain; charset=us-ascii |
|---|
Stan Wheeler wrote:
>
> Walter,
>
> This probably won't be much help but, by any chance, did the
> student specify Type 1 F-tests ?
yeah, I thought of that, but no he didn't. And if he had, it's unlikely
the dummy main effect p-values would have matched. I'll see about
posting the data.
> Also, I think that random intercept is the same as CS so I'd try
> rerunning with
> repeated / type=cs subject=group;
> in place of the random statement just to see if I got the same result.
we'll give that a try.
thanks,
-walt
Walter Davis walter_davis@unc.edu
Health Data Analyst
Odum Institute for Research in Social Science ph: (919) 962-1019
UNC - Chapel Hill fax: (919) 962-8980
|
