Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Giacomo Pallaro <giacomo.pallaro@studenti.unipd.it> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: xtivreg2 with lagged variables |
Date | Tue, 22 Oct 2013 12:33:07 +0200 |
Dear statalist, I'm running on Stata 12 some IV regressions using xtivreg2 on panel data and I am wondering whether it is possible to avoid the varlist1 variables to be employed into the first stage. If I use xtivreg2 depvar married age age2 (L.endog_var = L.instrument1 L.instrument2), fe I get First stage: L.endog_var on L.instrument1 L.instrument2 married age age2 Second stage: depvar on L.instrumented_var married age age2 but for me it is pointless to have - married age age2 - in the first stage while predicting a variable that is one period back in time. I wuold like to have - L.married L.age L.age2 - to be coherent with L.endog_var. The second stage instead is correct as it is since the endogenous variable shall be lagged in time with respect to the depvar. I tried to run xtivreg2 depvar married age age2 (L.endog_var = L.instrument1 L.instrument2 L.married L.age L.age2), fe what comes out is that the second stage is the same as before, while the first stage becomes: L.endog_var on L.instrument1 L.instrument2 married age age2 L.married L.age L.age2 and unfortunately is not what I need. What can I do to reach my goal? Best regards, Giacomo Pallaro * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/