Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: test for heterogeneity

From   Stas Kolenikov <>
Subject   Re: st: test for heterogeneity
Date   Thu, 7 Oct 2004 14:18:27 -0400

Looks like this calls for an interaction term. Does -sts , test-
syntax allow for that? If not, then you would need to generate the
interaction (the product of the indicators) and put it into -streg-.


On Thu, 7 Oct 2004 13:28:38 +0100, Anthony Moorman
<> wrote:
> I need to perform a test for heterogeneity in the following situation:
> A log-rank test - sts test - showed a significant difference in outcome
> between subgroups A and B.
> The results of a repeated test stratifying by treatment X and Y -
> strata(treatment) detail - suggested that the difference between A and B
> only occurred with treatment Y.
> I want to perform a test for heterogeneity to determine whether the effect
> between A and B is the same within the two treatment groups X and Y. How can
> I do this is Stata?

Stas Kolenikov
*   For searches and help try:

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