Hessian matrix mixed logit

This forum is for posts covering broader stated choice experimental design issues.

Moderators: Andrew Collins, Michiel Bliemer, johnr

Hessian matrix mixed logit

Postby cdelamaz » Wed Aug 03, 2016 1:57 am

Dear all, I am trying to understand how to estimate an efficient design for a mixed logit model.

I reviewed NGENE appendix section and the paper Bliemer, M. C., & Rose, J. M. (2010). Construction of experimental designs for mixed logit models allowing for correlation across choice observations. Transportation Research Part B: Methodological, 44(6), 720-734.

In both, the Hessian formula is shown in general terms. I have been struggling to derive the Hessian myself in more detail.

Can you recommend me a text where a detailed mathematical derivation for the Hessian is presented?

Thanks

Cristobal
cdelamaz
 
Posts: 8
Joined: Fri Aug 14, 2015 8:41 am

Re: Hessian matrix mixed logit

Postby johnr » Sat Aug 20, 2016 7:39 pm

Unfortunately not really - this took us years to derive, program, test, etc. I'm not aware that it has been reported elsewhere.

John
johnr
 
Posts: 171
Joined: Fri Mar 13, 2009 7:15 am


Return to Choice experiments - general

Who is online

Users browsing this forum: No registered users and 28 guests

cron