Is there a big difference in p-values? Whatever the tests, if one gives .03 and the other is insignificant, I'd say you have a "firm maybe". If you want to be rigourous, then you need to specify what test you will use before seeing the results, and it's obviously too late for that.
-------------------------------------------
Emil M Friedman, PhD
2304 Richmond Road
Beachwood, OH 44122
[log in to unmask]
216-591-1750 (voice)
775-249-6744 (fax)
----- Original Message -----
From: "Eve Corda" <[log in to unmask]>
To: <[log in to unmask]>
Sent: Friday, August 01, 2003 8:31 AM
Subject: QUERY: Fixed-effects testing in linear mixed-effects models
Dear all,
I'm using the MIXED procedure in SAS and I have encountered a difficulty with fixed-effects testing since the test result depends on the method used. A factor is found significant with the Kenward-Roger method whereas it is found non-significant with the Satterthwaite method. I know this is a classical problem but I don't know enough things about these methods to be able to know which one I should rely on. Could anyone provide me some references or websites, or maybe a simple advice if the situation is actually simple?
Thanks a lot for your time,
Greetings,
Eve CORDA
Office national de la chasse et de la faune sauvage
(http://www.oncfs.gouv.fr)
BP 20
78612 Le Perray en Yvelines Cedex
FRANCE
Phone: +33 (0)1 30 46 60 64
Fax: +33 (0)1 30 46 60 99
[log in to unmask]
|