I have a set of survey data that consists of answers to 10 knowledge questions along with demographic information about the respondent.

Our question of interest is to identify which demographics are most lacking in their knowledge of specific topics. Right now I am thinking of modeling each question as a binary outcome (correct/incorrect) and using logistic regression to gauge the relationship with demographic characteristics.

My question is whether or not there is an issue with doing this process 10 different times (1 for each question). The questions each cover knowledge of a different topic, but using 10 different models seems a little sketchy to me and I was wondering if I should be concerned.

  • $\begingroup$ Welcome to Cross Validated! Can you elaborate why you think it would be "sketchy" to run 10 separate models? Are any of the questions related to one another? $\endgroup$ – Marquis de Carabas Apr 19 '15 at 21:58
  • $\begingroup$ are you asking if there is something like a bonferroni correction for regression models? if so, please edit your question (i think that's a good question fwiw) $\endgroup$ – Anthony Damico Apr 20 '15 at 3:25

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.