|Date: ||Mon, 12 Aug 2002 13:02:04 +0100|
|Reply-To: ||Simone Leber <firstname.lastname@example.org>|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>|
|From: ||Simone Leber <email@example.com>|
|Subject: ||Welch-James and Brown-Forsythe|
|Content-Type: ||text/plain; charset="iso-8859-1"|
thanks so much for your help, it works fine and seems to be the right thing
to do, even if it's not the Welch-James Test. I was really just looking for
something to substitute the 2way ANOVA in the case of unequal variances, and
Brown-Forsythe seems to do the trick as well. So thanks for that!
The reference I've got for the Welch-James procedure is Algina, J. &
Olejnik, F.(1984). Implementing the Welch-Lames procedure with factorial
designs. Educational and Psychological Measurement, 44, 39-48.
2F2, 8 Thistle Place
++44/ 131/ 228 6471