[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Survey data correction for population
I would appreciate advice on the following issue:
I am trying to compare the population rates of a hospital-related
diagnosis among children in 4 different regions in the country. The
database that I am using is a sampling of all hospital discharges
(adults and children) in the US and contains strata, PSU and weights
needed for survey estimations. I can use the following to get estimates
of the number of diagnoses in each region:
svytotal diagnosis, by(region)
I am interested, however, in comparing the rate of the diagnosis per
100,000 regional population (not per number of regional hospital
discharges) in the four regions in a pairwise fashion. Based on census
data, I know the regional populations to be pop1 through pop4 for the
I would also like to compare the rate of the diagnosis in each region
according to age groups is a pairwise fashion.
Any advice? Do I need to add a second weight that represents the
relative contribution of each discharge to the entire population?
Randall S. Burd, M.D., Ph.D.
Division of Pediatric Surgery, Department of Surgery
Box 19, 1 RWJ Place
Robert Wood Johnson Medical School
New Brunswick, NJ 08903
* For searches and help try: