Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Maarten buis <maartenbuis@yahoo.co.uk> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: linear probability model |
Date | Wed, 23 Jun 2010 15:55:56 +0000 (GMT) |
--- On Wed, 23/6/10, dk wrote: > i have read some where that linear probability model > fits best for very large sample, where maximum > likelihood with probit and logit does not work can > any one explain this. I don't think that sample size is an issue anymore when it comes to the choice between linear probability model and logit/probit. I could imagine that such an argument played a role say thirty years ago, as the linear probability model can be estimated in one itteration, while maximum likelihood typically requires multiple itterations. However, with the current machines the kind of dataset would have to be so incredibally huge before that would become a problem, that you would have run into other problems long before that. Hope this helps, Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl -------------------------- * * 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/