Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: xi: sw poisson, p-values of variables rather than categories of them


From   Roger Newson <roger.newson@kcl.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xi: sw poisson, p-values of variables rather than categories of them
Date   Thu, 12 Dec 2002 15:42:25 +0000

At 15:57 12/12/02 +0100, A.M. Vos wrote:
Now here's another question about my poisson regression.
again, I'm performing something like:
-xi: sw poisson patient i.origin i.age i.durstay etc... forward-
than what I get is a list of p-values that are below -pe- of CATEGORIES
included in the model. (e.g. _Iorigin_2, _Iorigin10, _Iage1, _Iorigin7
etc.)

But what I would like to know is which VARIABLES (origin, age, durstay,
etc) are significant, rather than values (representing categories) of
those.

If you want to do chi-squared tests, then use -testparm- to test multiple dummy variables at the same time. Type -help test- and/or read -[R] test- to find out more. For instance, you might type

testparm _Iorig*

to do a chi-squared test for origin.

However, it must be stressed that there are issues involved here other than simply using the right Stata command. For instance, if you do a lot of significance tests, then you run the risk of selecting the 5% of results that are significant at the 5% level. I don't know much about the background to Annelies's project. However, quite often, if a customer wants to calculate P-values, then there is often a confidence interval that the customer really wanted.

I hope this helps.

Roger



--
Roger Newson
Lecturer in Medical Statistics
Department of Public Health Sciences
King's College London
5th Floor, Capital House
42 Weston Street
London SE1 3QD
United Kingdom

Tel: 020 7848 6648 International +44 20 7848 6648
Fax: 020 7848 6620 International +44 20 7848 6620
or 020 7848 6605 International +44 20 7848 6605
Email: roger.newson@kcl.ac.uk

Opinions expressed are those of the author, not the institution.

*
* 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