LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (September 2005)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Tue, 6 Sep 2005 09:38:41 -0400
Reply-To:     "Chan, Loretta" <Loretta_Chan@klinegroup.com>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Chan, Loretta" <Loretta_Chan@klinegroup.com>
Subject:      Scheffe VS Trimming Sample Sizes
Content-Type: text/plain; charset="US-ASCII"

Dear list,

I was given 3 data series and told to conduct a test to compare 3 groups of means. After looking at the uneven sample sizes of the 3 groups (60 VS 40 VS 25), I ran an ANOVA and the Scheffe test. I was subsequently told to trim off the excessive data points. In other words, I am to run ANOVA and a contrast with 3 groups of 25 cases each.

If my memory serves me right, I was told to avoid throwing away data if I can find an equally robust technique to achieve the same goal. Are there deficiencies in the Scheffe test that I am not aware of? Is it better to perform a contrast or a post-hoc Scheffee?

Thanks!

Regards, Loretta Chan

Data/Statistical Analyst


Back to: Top of message | Previous page | Main SPSSX-L page