I need confidence intervals for an o/e metric based on a continuous variable (observed days/ expected days) sumed up for all the people in the population.

  • $\begingroup$ What have you tried? What distributions are you assuming? Have you considered bootstrapping? $\endgroup$ – Björn Feb 8 at 7:30
  • $\begingroup$ fishers and midpoint used by standardized mortality ratio, but that isn't correct. I've considered bootstrapping. The observed and expected will both be right-skewed. $\endgroup$ – user123328 Feb 8 at 17:50

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.