Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

st: Panel data and IV GMM, please need some guidance

From   FredVer <>
Subject   st: Panel data and IV GMM, please need some guidance
Date   Sun, 10 Jun 2012 09:37:23 -0700 (PDT)

Dear all,

I have the question if data have a panel structure, with unique identifiers
over time and specified for 20 countries...Do you need to run a xtivreg2
regression per se or will a ivregress gmm regression also suffice?

The problem is I already have run an ivregress gmm regression, as my data
show heteroskedasticity and the diagnostic tests look good. I have chosen
this model as the leading paper does not include time anymore, so the
variables are averaged over the period under study. Now my supervisor
expected that I would run a panel data analysis...but that is not what I've

Can i motivate why I did not make use of my panel structure and more it wrong? As I have a week to deliver my final version, I
would really appreciate if someone could tell me if this regression is no
good and what would be I need to run al the regressions again
and now with xtivreg2?

View this message in context:
Sent from the Statalist mailing list archive at
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index