Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

st: Panel unit root, heteroskedasticity and autocorrelation


From   "Terzopoulou, Eleftheria" <et268@exeter.ac.uk>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Panel unit root, heteroskedasticity and autocorrelation
Date   Thu, 16 Jun 2011 14:00:35 +0100

Dear Statalisters,

I am running panel with linear model(in logarithmic terms) and I found unit roots when I test with Levin Lin Chu statistic but when I check time trend and substruct the cross-sectional means it yields I(0) variables. This means that FE estimation gives correct results since it does demeaning or not? If I retrieve the combined residuals and apply the test, can it be considered as a test for cointegration?
After that I found autocorrelation applying xtserial command and also heteroskedasticity applying xttest3 command. Thus I have more problem. I found the command xtpcse that has as choices autocorr and heteroskedasticity but does it assume corr(u_i, X)= 0 as in random effects? I am in trouble because I dont know how to solve the problem. Applying Hausman's test I take the FE as preferred but the problem of autocorrelation and heteroskedastity remains.Is there any option in FE for these?

Could anyboby help me?

Thank you in advance
Elli

*
*   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   |   Site index