Hello all.
I am looking at some medical outcome (hospitalization) before and after
some external event (reimbursement change). I have data on hospitalizations
over time in a well-defined population (a state). Specifically, I have the
number of hospitalizations by year (1995, 1996, etc), as well as the
corresponding population denominators for each year.
One question that I am asking is whether there was a before/after
difference in hospitalization rates.
I could use Poisson regression, or, negative binomial, to account for
extra-Poisson variation. However, I am worried that this may not account
for the fact that repeated hospitalizations can be observed on the same
subject. In other words, the hospitalizations may not be independent since
many will be for the same individual (the proportion of repeat
hospitalizations is not trivial, by the way), and that would invalidate my
standard errors.
I have no link to individual patients, i.e., I only have aggregate numbers
of hospitalizations.
I am thinking of using a GEE approach to fix up my standard errors. I could
define strata on the basis of year (and possibly race, age, and gender) and
use -xtgee..., i(strata)-
Comments on this?
Any other ideas as to what I can do? How do others treat such problems with
recurrent events?
Thanks,
Constantine
The documents accompanying this transmission may contain confidential
health or business information. This information is intended for the use of
the individual or entity named above. If you have received this information
in error, please notify the sender immediately and arrange for the return
or destruction of these documents.
________________________________________________________________
Constantine Daskalakis, ScD
Assistant Professor,
Biostatistics Section, Thomas Jefferson University,
211 S. 9th St. #602, Philadelphia, PA 19107
Tel: 215-955-5695
Fax: 215-503-3804
Email: [email protected]
Webpage: http://www.kcc.tju.edu/Science/SharedFacilities/Biostatistics
*
* 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/
