Bookmark and Share

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


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

st: Question on dynamic panel estimation


From   "Palan, Stefan ([email protected])" <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: Question on dynamic panel estimation
Date   Wed, 17 Jul 2013 08:47:31 +0200

Hi everybody,

I have data from an experiment with 4 treatments, each with 6 markets, of which each again has 15 periods (So in Treatment 1, I have markets 1, 2, 3, 4, 5 and 6, and 15 observations each. In Treatment 2, I have markets 7, 8, 9, 10, 11 and 12, each again containing 15 periods). I would like to determine whether there are differences in the intercept and slope of the market price between the treatments (which are fixed within markets). Markets are independent of each other, but periods within a market are not. In other words, I expect there to be autocorrelation in observations of consecutive periods (at least at lag 1, possibly at more).

Now I am not sure how to get the information I want. If I estimate using xtabond, I lose any information on intercepts, since it uses first differences, right? I can use xtmixed with a random intercept for each market and including the lagged price as an independent variable, but does that lead to correct standard errors/consistency/...?

I hope someone can help me...

Best regards,
Stefan.

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


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index