[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: P value in logistic regression models

From   "Martin Weiss" <>
To   <>
Subject   st: RE: P value in logistic regression models
Date   Sun, 20 Dec 2009 00:32:08 +0100


See the [SVY] manual, p. 76: " svy commands use t statistics with n - L
degrees of freedom to test the significance of coefficients, where n is the
total number of sampled PSUs (clusters) and L is the number of strata in the
first stage."

The page number for the Stata 10 manual may of course differ. Watch out for
the introduction of the "svy estimation" entry.


-----Original Message-----
[] On Behalf Of Jeanette Somlak
Sent: Sonntag, 20. Dezember 2009 00:20
Subject: st: P value in logistic regression models


I am a student analyzing data from a Canadian survey for my honours project.
I am using Stata version 10. I am successfully running a number of logistic
regression models. But I have a question:  What *test* is the p value for in
my logistic regression analyses (i.e. in the output table: p>|t|)? Adjusted
Wald test with t distribution?

Here is an example of my syntax:

svy, subpop(femalesubpop_postsepviol): logistic postsepviol aborig_recode
age5 children_ex

Any help would be much appreciated.

Thank you!

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index