st: I can't make autocorrelation go away in xtpcse

[Jose Aleman <alemanfordham.edu@gmail.com>]

Dear Stata team members,

I'm using xtpcse to estimate an error correction model with country
and year fixed effects. That is, I'm regressing the dependent variable
on its lag, plus every X variable and their lags. A Lagrange
multiplier test reveals a chi-square of 8.533 on 1 degree of freedom.
This indicates the hypothesis cannot be rejected that there is serial
correlation in the model. After using the correlation (ar1) and
correlation (psar1) options to correct this autocorrelation, I cannot
make this go way. Is there any way to address this issue?

Thank you,

Jose A. Aleman, Ph.D.
Assistant Professor
Political Science Department
Fordham University
http://faculty.fordham.edu/aleman
http://us.macmillan.com/laborrelationsinnewdemocracies
*
*   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/