Hi,
You can just do this manually - eg if you have 2 levels in your nested
logit, at the last level, estimate for example a conditional logit (or
whatever you are using). Construct the inclusive value from this - the log
of the denominator from the cond logit - and include this as an additional
regressor in the next step, ie for the first level. Estimates will be
consistent but will have incorrect std errors.
Regards,
Emla.
From: "Wei Tan" <[email protected]>
Reply-To: [email protected]
To: [email protected]
Subject: st: two step method for nested logit
Date: Mon, 23 Jun 2003 23:46:42 +0800
Hi,
Is there any way in stata to specify two step method to estimate nested
logit model. It takes too long for stata to estimate the nested logit model
by full information maximum likelihood. I would like to get the result
fast.
thanks
_________________________________________________________________
MSN 8 helps eliminate e-mail viruses. Get 2 months FREE*.
http://join.msn.com/?page=features/virus
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
_________________________________________________________________
On the move? Get Hotmail on your mobile phone http://www.msn.co.uk/msnmobile
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
