I have looked at the risk of hospital admission in the general population and in those with lung disease when exposed to an environmental toxin. The patients with lung disease are also part of the general population. My results look as follows:

Population  percent_increase    lcl    ucl     pvalue
All           0.44              0.09    0.80    0.02
Lung disease  1.24              0.31    2.18    0.01

The results shows there is an increased risk in both groups. But the risk in those with lung disease is larger then the general population (about 2.8 times to be more specific).

My question is: if I claim those with lung disease have a 2.8 times more risk than the general population is the conclusion wrong? If I really want such conclusion what should I do in the analysis?

  • $\begingroup$ It sounds like you want to know if having lung-disease modifies the estimated effect that exposure to the toxin has on hopspital admission. To elict more answers from people, I would suggest that you post the raw data in the form of two 2X2 tables (Exposure X Outcome, in those with and without lung disease). $\endgroup$ – D L Dahly Feb 26 '15 at 10:42

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.