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: Missing standard error of constant term

From   Maarten Buis <>
Subject   Re: st: Missing standard error of constant term
Date   Thu, 16 Jun 2011 21:22:55 +0200

On Thu, Jun 16, 2011 at 7:44 PM, Nyasha Tirivayi wrote:
> Thanks for your reply. I am doing the logit regression for propensity
> score matching. And I really needed the community dummies in the model
> to control for any unobserved community effects. So your suggestion
> would be for me to  drop them completely? I checked and there are
> sufficient observations per community.

Hard to say, that depends on what exactly the problem is. The devil is
in the detail in such situations. So I would just look at lots and
lots of cross tabulations and graphs to see if I can identify the
problem. As I said, I suspect a coding error or a reference category
that is not left out, or one or more too small comunities, but it
could be many other things.

-- Maarten

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

*   For searches and help try:

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