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:         Thu, 15 Sep 2005 10:12:17 +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: family-wise error rate in post-hoc tests
In-Reply-To:  <OF4E151199.BC627ABE-ON8525707C.006C0575-8525707C.006DBE63@cancer.org>
Content-Type: text/plain; charset=ISO-8859-15

Hi Christina,

CM> I have a question regarding the Tamhane's T2 as a post-hoc test in CM> multiple linear regression analysis.

Tamhane's T2 test is a post-hoc test suitable for comparing means when the homogeneity of variances assumption is not met. It's a really conservative procedure: t tests with unequal variances, followed by Sidak's p-values adjustment method. Sidak's method is slightly less conservative than Bonferroni's, but offers a strict control of the FWER at alpha=0.05.

It's use in multiple regression analysis surprises me, because HOV is a condition to use MR, and Tamhane's test, as I said, is used when heterogeneous variances are found. Why are you using it instead of Tukey, or Bonferroni, Scheffee...?

CM> Does SPSS automatically set the family-wise error rate at CM> alpha=0.05?

Of course

CM> My guess is that the family-wise error rate is set CM> at alpha= 0.05 for all of the post-hoc options that are listed but CM> I am having difficulty confirming that when I reviewed the SPSS CM> documentation. Does anyone know the answer and if so is there a CM> reference?

Have you checked the 'Algorithms' folder in your installation CD? If you don't have access to it, then you can find a detailed description and references for every post-hoc method here:

http://support.spss.com/tech/stat/Algorithms/13.0/app10_post_hoc_tests.pdf

(if requested to login, use 'Guest' both as User & Password)

Regards, Marta mailto:biostatistics@terra.es


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