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

st: re: SUR and unbalanced panel data

From   Kit Baum <>
Subject   st: re: SUR and unbalanced panel data
Date   Sat, 10 Nov 2007 12:51:17 -0500

Alessia said

I am writing cause I have a quetion related to that of Conny. I want
also to run a SUR on a panel data (strongly balanced). However, with
SUREG I think you just run a normal OLS regression, and not a panel
random or fixed effects regression. Is that right? I am then asking
how to apply with stata a SUR on panel data.

First of all, as the cited book discusses, SUR can be considered a panel data estimator, but data must be reshaped to the wide structure to be used in SUR, unlike the long structure appropriate for fixed- or random-effects estimators (e.g. -xtreg-).

I developed a version of -sureg- that works with unbalanced panel data -- that in which not all the panel units have the same observations -- and would be glad to make it available to Alessia, as I did for Conny. It is not yet ready for public release, and it does not handle constraints across equations.


Kit Baum, Boston College Economics and DIW Berlin
An Introduction to Modern Econometrics Using Stata:

* For searches and help try:

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