.xtabond g l(2/4).g l(1/4).f .xtabond f l(2/4).f l(1/4).g which is to test Granger causality between the two variables. It amounts to testing if the coefficients of all the lags of the other variable are statistically significantly different from zero. Do all these procedures seem to be correct?? I have also deliberately chosen 4 lags, because I do not know how to choose the optimal lag structure for the panel VARs. Could someone let me know of such a command?? Thanks for any help you can provide. Quoc Binh __________________________________ Do you Yahoo!? The all-new My Yahoo! - What will yours do? http://my.yahoo.com * * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/