Bookmark and Share

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

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

Re: st: Poisson regression -not concave-

From   "Michael N. Mitchell" <>
Subject   Re: st: Poisson regression -not concave-
Date   Sun, 06 Jun 2010 21:15:43 -0700


I would suggest that you try making a simple crosstab of the "dummy" variable by the dependent variable. I think that will show that the outcome variable cannot be zero when the dummy variable is 1. It is possible that the estimation command is "bothered" by this determinacy between the predictor and outcome, creating a situation where the procedure cannot converge. I am sure that others could provide a more technical and detailed explanation, but I hope this is helpful.

Best regards,

Michael N. Mitchell
Data Management Using Stata      -
A Visual Guide to Stata Graphics -
Stata tidbit of the week         -

On 2010-06-06 9.07 PM, Paolina Medina wrote:
Stata listers,

I'm trying to run a poisson regression model in which the dependent
variable is the number of mobile phones from the households, and among
other explanatory variables i am using a dummy wariables which takes
the value of 1 when the household has at least one cell phone and zero

But it turns out that whenever i use that dummy variable the iterative
process in stata does not converge, and it can be read for example:
iteration 380: log likelihood = -7734.6891  (not concave)

It i drop that dummy variable i get convergen at Iteration 3:   log
likelihood = -7734.6927

Does anyone has any suggestion or explanation?
And where can i get more information about the numerical process
behind the maximum likelihood estimation?

Thank you very much in advance.

*   For searches and help try:
*   For searches and help try:

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