Date:         Thu, 1 Jul 2004 19:20:50 +0200
Reply-To:     Marta García-Granero
              <biostatistics@terra.es>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Marta García-Granero
              <biostatistics@terra.es>
Organization: Asesoría Bioestadística
Subject:      Re: Brown-Forsythe and Welch
In-Reply-To:  <s0e4406c.033@MAINCF1P.cf.ac.uk>
Content-Type: text/plain; charset=ISO-8859-15

Hi Paul,

PM> I have a user who has done a OneWay Anova and the variances are shown to be
PM> unequal, she then obtains the Robust Test for Equality of Means (Welch and
PM> Brown-Forsythe).

To my knowledge (sorry, no refs at hand):

Under normality and variance heterogeneity, the Brown-Forsythe and the
Welch test perform well over a wide range of parameter configura-
tions, but the Welch test becomes liberal when the sample sizes are
small and the number of groups is large.

I downloaded a copy of an article I found useful:

http://www.sfb475.uni-dortmund.de/berichte/tr32-01.ps

Regards

Marta Garcia-Granero, PhD
Statistitian