Dear Statalist members,
I have encountered considerable problems in using the 'aflogit.ado'
program (STB-42 sbe21) to estimate adjusted PAFs . These are
some of them:
1) Unable to estimate PAFs following conditional logistic
regression (clogit)
2) Unable to estimate PAFs following poisson regression with
aggregated person-years data and interaction terms between
explanatory variables
3) Error message ("option cc not allowed") when trying to use the
cc option (i.e. "aflogit, cc") to specify that data are from a case-
control design rather than a cross-sectional or cohort study.
4) Generation of invalid estimates when the 'if' command is used to
restrict the data set
Does anyone know a of simple and more reliable way of obtaining
adjusted PAFs following logistic, poisson and Cox regression
modelling?
Are there any plans to incorporate a flexible and valid adjusted PAF
estimator into future versions of Stata that can deal with a variety of
different regression models?
Is this currently possible in any other statistical packages?
Thanks and best wishes,
Roger Webb
Research Fellow
University of Manchester (UK)
*
* 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/
