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 agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.