Statalist The Stata Listserver

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

st: Comparing OLS and WLS results

From   "Himaz, F.R." <>
To   <>
Subject   st: Comparing OLS and WLS results
Date   Wed, 1 Mar 2006 09:54:43 -0000


I want to estimate a model using OLS and Weighted Least Squares (both
with standard errors adjusted for clustering) and then compare them.
The null hypothesis is to assume that both estimators are unbiased with
the regressions homogenous across strata.

If true, the difference between them will have an expected value of
zero.  However, if heterogeneity and design effects are important, the
two expecations will differ.

How can I perform such a test of comparison with Stata?  Thanks in
advance for any insight/suggestions.


*   For searches and help try:

© Copyright 1996–2020 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index