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

Re: st: glm error message after binomial ...

From (Roberto G. Gutierrez, StataCorp)
Subject   Re: st: glm error message after binomial ...
Date   Mon, 18 Feb 2008 15:43:32 -0600

Jane Schroeder <> writes:

> When I run binomial -glm- models with a log or identity link function I get
> the following error message whenever there are observations with missing
> data for a model covariate, even though all predicted risks are well within
> the permissible (0,1) range:

> Warning: parameter estimates produce inadmissible mean estimates in one or
> more observations.


and Maarten L. Buis <> replied:

> I think StataCorp forgot a -if e(sample)- in lines 1512 and 1516 of glm.ado
> (you can see that when you type -viewsource glm.ado-).  you can perform this
> test yourself by typing after -glm-:

> predict mu, mu
> assert mu >= 0 & mu <= 1 if e(sample)

Maarten is right, and we'll get this fixed in the next ado update.  In the
meantime, if Jane performs Maarten's suggested check she can safely ignore the

*   For searches and help try:

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