[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: variance of R2

From   "Maarten Buis" <>
To   <>
Subject   RE: st: variance of R2
Date   Wed, 8 Aug 2007 18:04:29 +0200

--- wrote:
> I need to compare the R2s from two different samples (as I wrote in my second
> message to statalist), as it is usually done in the literature I am currently
> studying, so I need to assess the statistical significance of the difference
> between two R2s

Why not do something like this:

*------ begin example --------
sysuse auto, clear
xi: reg pri I.foreign*mpg
testparm _I*
*-------- end example --------

Here you have two samples (foreign and domestic cars), and the output from 
-testparm- gives you a test that the constants and the effect of weight are
the same. Alternatively you could interpret the test as a test of the 
hypothesis that the R2 of the constrained model is the same as the R2 of the
unconstrained model. This is not a test of the hypothesis that the R2 in the
two samples are the same, as this hypothesis is non-sensical: any difference
in R2 could be due to a difference between samples in the amount of variance 
that is to be explained (TSS) and/or a difference in the amount of variance 
that can be explained (MSS). 

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology 
Vrije Universiteit Amsterdam 
Boelelaan 1081 
1081 HV Amsterdam 
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434 

+31 20 5986715


*   For searches and help try:

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