Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Brian P. Poi" <brian@poiholdings.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Levpet revenue versus valueadded option |
Date | Fri, 06 May 2011 20:22:47 -0400 |
On 05/03/2011 02:03 PM, Adriana Hauer wrote:
Dear all, Can somebody tell me whether a levpet command with revenue as an option delivers the same coefficient estimates as the SAME levpet command with valueaddd as an option? If not, why? Thanks! Lilly
Lilly,Even if you have a dataset that has the right variables to do both estimation with revenue as the dependent variable and value-added as the dependent variable, I don't think you will get the same estimates. The two estimators use slightly different techniques to disentangle the effects of the productivity shocks (because the dependent variables represent different concepts), so the final results will not coincide. If you have a large enough dataset, I think the two techniques should produce similar results assuming the Cobb-Douglas production function specification is valid, technology shocks do in fact follow a first-order Markov process, etc.
-- Brian Poi -- brian@poiholdings.com * * 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/