Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
You are getting different estimates because your arima command specifies an ARMAX model, that is, a model with ARMA(1,0) errors and an additional
regressor X. If you did not have the original regressor, then you could write the model either as an AR(1) model in y (with a lagged depvar) or
as a regression of y on x with AR(1) errors. But the arima that will reproduce your regress results, perfectly, is
arima y x L.y
which will give you large-sample standard errors rather than the finite-sample VCE from OLS.
Kit
Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html
*
* 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/