Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: transition probabilities

From   "Maarten Buis" <>
To   <>
Subject   RE: st: transition probabilities
Date   Wed, 16 May 2007 12:47:07 +0200

--- emre ekinci wrote:
> I know that ecah cell contains a known probability and a function of which
> parameters are to be I know that each the probabilities in each
> cell are uniqely determined.I am studying the identification restricitions
> in presence of attrition.I will use the refreshment sample to estimate this
> transition matrix(indeed a first order markov process).I need to learn two
> things:
> 1.How can I estimate this 3x3 matrix by using MLE in STATA?
> can I add some restrictions to my optimization problem?

Your question is still not very clear. People can't give you precise advice 
on how to do things if they don't know what the data looks like and what 
exactly the model is you want to estimate. Still, I have three general 

1) If you can write the likelihood function and the model is identified than 
it can be estimated by MLE in Stata. Worst-case scenario is that you'll have
to using the -ml- command, which is not that hard.
2) You probably can estimate these probabilities by estimating for each 
origin state a separate -mlogit- where the dependent variable is the 
destination, but this depends on the kind of data you have and the exact
markov model you want to estimate. 
3) Restrictions are typically handled using the -constraint- command. see:
-help constraint-

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology 
Vrije Universiteit Amsterdam 
Boelelaan 1081 
1081 HV Amsterdam 
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434 

+31 20 5986715

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index