Dear dr.Cordula,
if the problem is that the lagged explanatory variable is endogenous you can use the command "ivreg2" an extension of traditional ivreg that allows for GMM estimation and other possible estimation methods for dynamic panel data.
If there's not an endogeneity problem I know that "xtreg" command don't allow for time series operator. You have to proceed as follow
First step: generate lagged explanatory variable:
for example: generate x(t-1) ---"gen lagx(t) = l.x(t)"
The time series operator are
l. = lagged level
f. = led level
d.= first-difference
ld. = lagged level in first-difference
ecc.
than perform the traditional regression
xtreg x(t) lagx(t) ecc.
Best regards
Andrea Sisto
*
* 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/
