Statalist


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

st: Dynamic Panel Data Analysis with T=3


From   Mauro Caselli <mauro.caselli@economics.ox.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: Dynamic Panel Data Analysis with T=3
Date   Mon, 28 Jul 2008 17:39:55 +0100

Dear all,

I have a balanced panel dataset with T=3 and N=53 and I would like to  
estimate y_i,t = a + b y_i,t-1 + c x_i,t + d y_t + e_i + v_i,t. x_i,t  
is predetermined, but maybe to be relaxed, and y_t are time dummies.
I have tried the Anderson-Hsiao estimator and I know about the  
problems related with this estimator. So I wanted to try difference  
and system GMM, but in the first case I get that all the variables  
are collinear and so does not estimate anything, while in the second  
case it does not estimate anything apart from the estimates  
themselves (so no standard errors nor anything related to them).  
Therefore, I was wondering if the problem lies in the fact that T is  
only = 3 or with my code, which is the following:
xtabond2 y l.y x1 x2 y2 y3, gmm(y, lag(2 2)) iv(x1 x2 y2 y3) nolevel  
small

Thank you very much for your help.

Best,

Mauro



*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index