Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Shikha Sinha <shikha.sinha414@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: IV vs 2SLS |
Date | Fri, 3 Aug 2012 10:01:14 -0700 |
Thank you all for the wonderful suggestion. Now I am better informed about the difference between IV and 2sls. Thanks again, Shikha On Fri, Aug 3, 2012 at 5:03 AM, urbain thierry YOGO <yogout@gmail.com> wrote: > IV is a method while 2sls is an estimator such as GMM, ML or LIML. In > other words you are using an IV method means that you make use of an > instrument to solve the issue of endogeneity. Then you can't choose > between IV and 2sls but you can choose between GMM, LIML and 2SLS. For > instance look at the ivregress command in stata. When you use ivreg, > the standards errors are automatically corrected by stata. But when > you use reg and you recover the predicted value, you have to correct > the standard error. Then using ivreg or ivreg2 for me seems better > than computing standard error by hand (after reg). May be the boostrap > could handle this. Just check. > > 2012/8/3, Shikha Sinha <shikha.sinha414@gmail.com>: >> Dear all, >> >> What is the difference between IV and 2sls and which is the preferred >> method to correct for endogeneity (advantage and disadvantage)? >> >> (a) ivreg2 y x1 x2 (x3=z) >> >> (b) reg x3 z x1 x2 >> predict x3_hat >> reg y x3_hat x1 x2 >> >> By employing (a) and (b) I get similar coeff, but standard errors are >> different. >> >> Thanks, >> Shikha >> * >> * 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/ >> > > > -- > *Urbain Thierry YOGO > Ph.D candidate in Economics* > * > * 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/ * * 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/