Re: st: RE: probability models

[Roger Newson <roger.newson@kcl.ac.uk>]

At 12:35 07/03/2005, Nick Cox wrote (in reply to Blau Blau):
> For the normal, you have -ttest- and -ttesti-.
>
> A comparison of two Poisson means is
> possible using -poisson-. I am not
> aware of an immediate equivalent.
>
> Nick
> n.j.cox@durham.ac.uk
If you are really confident that the 2 Poisson variables you are comparing 
really are Poisson, then you can use the fact that the conditional 
distribution of the first one, given their sum, is binomial, with total 
equal to their sum, and probability equal to

mu_1/(mu_1+mu_2)

where mu_1 and mu_2 are the first and second Poisson population means. 
Therefore, you can use -cii- to define a binomial confidence interval for 
mu_1/(mu_1+mu_2), which should include 0.5 if mu_1 is equal to mu_2.

I hope this helps.

Roger


--
Roger Newson
Lecturer in Medical Statistics
Department of Public Health Sciences
Division of Asthma, Allergy and Lung Biology
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
Website: http://phs.kcl.ac.uk/rogernewson/

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/