Statalist


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

Re: st: Missing standard error and confidence intervall for a dummy


From   "georg wernicke" <georg.wernicke@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Missing standard error and confidence intervall for a dummy
Date   Fri, 10 Aug 2007 13:37:54 +0100

Hello Maarten,

thanks for the tip. I tabed the dummy with the select but it does not
seem that the dummy for which is not standard error etc is given
predicts the selection any better than the other dummies for which the
results are just fine. Also, the dummies coefficient comparably large.

Does somebody has another idea?

Thank you very much again,

Georg Wernicke

On 8/10/07, Maarten buis <maartenbuis@yahoo.co.uk> wrote:
> --- georg wernicke <georg.wernicke@googlemail.com> wrote:
> > I have used a heckman twostep selection process. After employing the
> > test I get 2 tables, the selection and the regression table. What
> > puzzles me, that in the one of the tables STATA gives me the
> > coefficient but does not report a standard error, confidence
> > intervall and the z value for a dummy but does so in the other
> > regression table.
>
> One possibility is that the dummy is a nearly perfectly predictor in
> the selection equation. The way to find that out is to look at a table
> of the selection variable against the dummy. You can do that as
> follows:
>
> gen select = !missing(y)
> tab select baddummy
>
> (Assuming that your dependent variable is called y and the bad dummy is
> called baddummy)
>
> Hope this helps,
> Maarten
>
> -----------------------------------------
> 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
>
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
>
>
>      ___________________________________________________________
> Yahoo! Answers - Got a question? Someone out there knows the answer. Try it
> now.
> http://uk.answers.yahoo.com/
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index