I am analysing the difference in risk of surgical complications beween
laparoscopic and open appendectomy in data from a large administrative
register. What i really want is to describe and analyse the risk in
three geographical areas after adjustment for a number ov covariates
(age, sex, diagnnosis at operation). I have done that by running
separate models for each geographical area and keep only the result
for the laparoscopy/open variable in the multivariate model like this:
Numbers
Area Open Laparoscop
Univariate Multivariate
Low volume 109/23352 (0.5%) 16/1992 (0.8%) 1.73 (1.02-2.92)
0.042 2.23 (1.28-3.89) 0.005
Medium 127/35599 (0.4%) 37/7309 (0.5%) 1.42 (0.98-2.05)
0.061 1.55 (1.04-2.30 0.030
High 224/41296 (0.5%) 122/13378 (0.9%) 1.69 (1.35-2.11)
<0.001 1.81 (1.43-2.28) <0.001
How can I make inference on the results of the multivariate models? I
assume there are other ways to analyse this in one single model. Any
comment are appreciated.
Roland Anderson
*
* 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/