Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Michael Barker <mdb96statalist@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: non-linearities in ml |
Date | Wed, 31 Jul 2013 10:16:03 -0400 |
"lf" can be used anytime the likelihood function can be written as the sum of independent observations. It does not mean that your likelihood function should be linear in parameters. The way you've written the likelihood function above, it looks like the lf model is appropriate. Mike On Tue, Jul 30, 2013 at 10:21 PM, Ishani Tewari <ishani.tewari@gmail.com> wrote: > Dear all, > I need to estimate a logit where the parameters (beta1,beta2,beta3) > enter very non-linearly:. > > lnf=ln(invlogit((X1^beta1')*(`beta2*X2+`beta3'*log(`beta3'/X1)))) if y1==1 > lnf=ln(invlogit(-(X1^beta1')*(`beta2*X2+`beta3'*log(`beta3'/X1)))) if y1==0 > > Can I (should I) still use the "lf" model? > > thnks > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/