Dear All,
I'm trying to estimate a system of engel curves, for few selected consumption categories, using an aggregated time-series cross-section data set.
The dataset includes 15 countries observed over a time period that goes from 1980 to 2005 (although some years for some countries are missed so it is an unbalanced dataset).
The model presents both serial correlation and correlation across equations and to correct for that I would like to use the the Parks-Kmenta method for AR(1) error term, in a SUREG framework.
Is there a built-in estimator doing that in STATA? I have read that the Parks-Kmenta method, with a specific option for sureg, is in stata but couldn't find it.
Any help would be very appreciated.
Best,
Ignazio
*
* 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/
