Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Misha Spisok <misha.spisok@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Error using diffvars() in -xtabond- |
Date | Mon, 7 Jun 2010 17:29:52 -0700 |
Hello, Statalist, I am encountering an error when attempting to use diffvars with -xtabond-. For example, . webuse abdata . xtabond n l(0/1).w l(0/2).(k ys), diffvars(yr1980-yr1984) lags(2) diffvars() may not be specified when performing system estimation r(498); With respect to the error message, I notice that the documentation for -xtabond2- includes a noleveleq option for difference GMM rather than system GMM (i.e., not including the equation in levels). However, I cannot find a similar option in -xtabond-. Is this the nature of the error? If so, how can I specify this in -xtabond-? Is this in inappropriate use of 'diffvars()' (as opposed to simply one that "merely" produces an error)? If this is inappropriate, is there a way of including a year dummy without using differences of year dummies as instruments? Or is this just plain inappropriate in this context? If it is appropriate, how how can one include year dummies without using differences of year dummies as instruments? Thank you for your time and attention. Best, Misha * * 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/