Re: st: Poisson Regression

[brendan.halpin@ul.ie (Brendan Halpin)]

On Sun, Feb 13 2011, Alexandra Boing wrote:

> I would like to know how to proceed and the justication Mathematical and
> Statistical. My dependent variable is spent on health (0=No   1=Yes).
> The prevalence was higher than 10 percent. Can I do Poisson regression?
> According to this paper published in BMC on line in 2003, registred  
> PMC521200 I can do Poisson regression with variable (0=No  1=Yes) and
> with prevalence higher than 10 percent, but other authors report that
> only I can do Poisson regression with the dependent variable= discrete
> variable and prevalence under 10 percent.
> Which is correct? And what is the explanation Mathematical and Statistical?Thanks, Alexandra

To come back belatedly to your initial question, I think this paper:

  Reichenheim and Coutinho (2010) "Measures and Models for Causal
  Inference in Cross-Sectional Studies: Arguments for the
  Appropriateness of the Prevalence Odds Ratio and Related Logistic
  Regression", BMC Medical Research Methodology

throws a lot of cold water on the idea that one should use poisson or
log-binomial instead of logistic when the baseline probability is above
0.10. They point out that while there are circumstances where log-bin,
poisson or Cox regression are correct, there is a wide range of
circumstances where logistic regression is better (and the baseline
probability is not one of the relevant criteria). 

Regards,

Brendan
-- 
Brendan Halpin,  Department of Sociology,  University of Limerick,  Ireland
Tel: w +353-61-213147 f +353-61-202569 h +353-61-338562; Room F1-009 x 3147
mailto:brendan.halpin@ul.ie  http://www.ul.ie/sociology/brendan.halpin.html

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/