Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Poisson MLE in Microeconometrics using Stata


From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: Poisson MLE in Microeconometrics using Stata
Date   Tue, 9 Nov 2010 16:05:12 +0000 (GMT)

I cannot follow your code, it does not look like a poisson to me.
When starting such an excercise I would start simple; e.g. I 
would start with recreating -poisson-, make sure that it works 
(you can compare your results with -poisson-), and than add, 
step by step, your complications. Trying to program a complicated
model in one go is tempting but it never works.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


--- On Tue, 9/11/10, Beatrice Crozza <[email protected]> wrote:

> From: Beatrice Crozza <[email protected]>
> Subject: st: Poisson MLE in Microeconometrics using Stata
> To: "statalist" <[email protected]>
> Date: Tuesday, 9 November, 2010, 15:07
> Dear All,
> 
> I want to estimate parameters of my model using a MLE, but
> assuming a
> Poisson distribution.
> 
> I have the book "Microeconometrics using stata" and there
> is a chapter
> for the count models and the Poisson, but they are related
> to a
> regression. Now, I am little bit confused. For my MLE I
> want to know
> the values of parameters that I cannot directly observe
> from my data.
> 
> How can I perform my MLE?
> 
> Following is my MLE without assuming Poisson for r,s and
> t:
> 
> program define mle
> version 10.0
> args lnf a d b n g
> 
> tempvar ma md mb  mn mg
> 
> quietly gen double `ma'=1-`a'
> quietly gen double `md'=1-`d'
> quietly gen double `mb'=1-`b'
> quietly gen double `mn'=1-`n'
> quietly gen double `mg'=1-`g'
> 
> quietly replace
> `lnf'=ln((`a')*(`d')*((((`b')*(`md')*(`g')+(`b')*(`mg')*(`g')*(`n'))^r)*(((`mb')*(`mo')*(`g')+(`mb')*(`mn)*(`ma')*(`n'))^s)*(((`b')*(`md')*(`mg')*(`mn'))^t)*(((`mb')*(`mn')*(`ma')*(`g'))^s)*(((`b')*(`mg')*(`md')+(`mb')*(`b')*(`n'))^t)))
> 
> end
> 
> Now, to assume a Poisson distribution for r, s and t, I
> need only to
> rewrite my code in a way that they follow a Poisson or I
> have also to
> specify something in the mle?
> 
> Moreover, if I observe overdispersion in the book is
> suggested to use
> the option VCE to obtain a robust estimate of the
> variance-covariance
> matrix. How can I reach the same result in my mle program?
> 
> Could you please help me?
> 
> Thank you very much.
> 
> Bast,
> Bea
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/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/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index