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: Marginsplot after Poisson regression and negative predicted values
From
"Roger B. Newson" <[email protected]>
To
[email protected]
Subject
Re: st: Marginsplot after Poisson regression and negative predicted values
Date
Wed, 08 Jan 2014 10:44:52 +0000
I think this example is part of the reason why most people use a log
transform with Poisson means. THe -punaf- package (downloadable from
SSC) uses this transformation, both with scenario Poisson means and with
their ratio. And -punaf- works for Poisson-like count variables, and
even for gamma and inverse-Gaussian continuous variables. And even with
life expectancies, as estimated using -streg-.
Best wishes
Roger
Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology, Occupational Medicine
and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
UNITED KINGDOM
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Email: [email protected]
Web page: http://www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/
Opinions expressed are those of the author, not of the institution.
On 08/01/2014 09:37, Maarten Buis wrote:
I suspect that you mean the confidence interval around the predicted
values. It is a known issue with the delta method that is used by
-margins- for computing the confidence interval. Generally I would not
worry too much about it, as these bounds are failry approximate
anyhow, but if you do you can predict the linear predictor with its
confidence intervals and transform those to the expected count metric
as in <http://www.stata.com/support/faqs/statistics/delta-rule/index.html>.
Hope this helps,
Maarten
On Wed, Jan 8, 2014 at 9:51 AM, James Bernard <[email protected]> wrote:
Hi all,
I have ran a Poisson model. Then tried to run -margins and
-marginsplot for one of the variables.
The shape of the graph makes sense. But, the range of predicted values
of the dependent variable (which is a count variable, obviously)
ranges from 1 at its maximum and -6 at its minimum. Is this usual? Am
I doing something wrong?
Thanks,
James
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/