Well, the name pretty much says it all. I have searched high and low, but I cannot find a concrete answer to the following question(s):

How would one interpret the incidence rate ratio for a poisson regression with a non-binomial dependent variable? Also, can this be generalized? i.e. will the interpretation be the same for any count model or does it differ by model?

  • $\begingroup$ Do you mean a "rate ratio" as defined here: en.wikipedia.org/wiki/Rate_ratio? If so, how does the question relate to econometrics (maybe I'm missing something but it appears to relate to medical statistics)? $\endgroup$ – Adam Bailey Apr 7 '16 at 9:53
  • $\begingroup$ Yes it is the same but it is used to determine causal effects of count models since regression results do not have the typical interpretation in such models, so it has applications outside of medical statistics and is often reported in economic papers using count models. $\endgroup$ – DornerA Apr 7 '16 at 11:04
  • $\begingroup$ The following may be useful: ats.ucla.edu/stat/stata/output/stata_poisson_output.htm $\endgroup$ – Adam Bailey Apr 7 '16 at 19:19

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.