Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "Nick Cox" <n.j.cox@durham.ac.uk> |
| To | <statalist@hsphsun2.harvard.edu> |
| Subject | RE: st: RE: Different coefficient magnitudes in ols and 2sls estimation |
| Date | Thu, 22 Apr 2010 19:39:24 +0100 |
I don't know more than I am saying here, but yes, I imagine you could look at what kind of differences you expect under a realistic data generation process. Nick n.j.cox@durham.ac.uk -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Sukesh Patro Sent: 22 April 2010 19:37 To: statalist@hsphsun2.harvard.edu Subject: Re: st: RE: Different coefficient magnitudes in ols and 2sls estimation Nick, Do you mean we sub-sample and run both OLS and 2SLS (say n=1000 times), get the coefficient distributions from each and compare? On Thu, Apr 22, 2010 at 1:30 PM, Nick Cox <n.j.cox@durham.ac.uk> wrote: > Simulate and see is my only suggestion. > Nick > n.j.cox@durham.ac.uk / * * 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/