st: xtlogit versus gllamm

[Isabella Image <Isabella.Image@dwp.gsi.gov.uk>]

Dear all,

My question is regarding use of xtlogit versus gllamm to calculate random effects for a binary response model. I am interested in the estimation methods that have been used.

a) As far as I am aware posterior means cannot be found after xtlogit . Is this because of something not calculated - if so what is it that gllamm does that is different?

b) I can set up both gllamm and xtlogit to be using the same estimation technique (eg. both adaptive GH quadrature, 12 quad points). However, the parameters are still not the same (from the first decimal place). Is there any other major estimation difference that I am missing?

I see Sophia has a book out on this soon, but sadly I think this may come too late for my dissertation.

Bella

The original of this email was scanned for viruses by the Government Secure Intranet (GSi) virus scanning service supplied exclusively by Energis in partnership with MessageLabs.

On leaving the GSi this email was certified virus-free

This document is strictly confidential and is intended only for use by the addressee. 
If you are not the intended recipient, any disclosure, copying, distribution or other 
action taken in reliance of the information contained in this e-mail is strictly prohibited.
Any views expressed by the sender of this message are not necessarily those of the Department 
for Work and Pensions.
If you have received this transmission in error, please use the reply function to tell us 
and then permanently delete what you have received.
Please note: Incoming and outgoing e-mail messages are routinely monitored for compliance 
with our policy on the use of electronic communications.