Hi, I've tried 2 times earlier to find somebody who could give advice on cointegration analysis in Stata, so far nobody has answered. Here is the last attempt: is it possible to estimate models with restrcitions on the short term coefficients (i.e. uneven lag lengths in the underlying VAR) and also to include exogenous variables? Next: Stata offers 5 different trend and constant term specifications; how are the constant terms identified in the case where an intercept is included both in the VAR and in the cointegrating equation (+ a trend in the CE)? Lutkepohl/Kratzig recommends that there should should be only intercept due to identification problems (cf. their free software JMulti).
Best regards,
Svein.
*
* 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/
