Date: Thu, 14 Aug 1997 13:21:15 -0400
Sender: "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From: Jr Bowers <jb129@COLUMBIA.EDU>
Subject: Logistic Regression & Design Effect
Content-Type: TEXT/PLAIN; charset=US-ASCII
I am using a large national database created by the National Center for
Education Statistics call the National Education Longitundinal Study
1988. The sample is a probability culster sample and to allow for sampling
error it is appropriate to adjust the statistical findings by the design
With linear regression the adjustment is made by dividng the t statistic
by the square root of the desigh effect or dividing the F statistic by the
design effect. I am using logistic regression rather than linear
Is there a statistic comparable to a t statistic or F statistic in the
SPSS logistic regression ouput? If so, what is it. Is it comparable to a
t statistic or an F statistic?
Thank you very much for giving this question your attention.
Unification Theological Seminary
10 Dock Rd.
Barrytown, NY 12507