I have a sample that consists of large, medium, and small firms and i want to run a separate regression for each size group. When I winsorize a variable should I do it for the whole sample (i.e. select the variable in the whole sample) or for each size group alone (i.e select the large firm subsample and winsorize it for the subsample)?

  • $\begingroup$ Why separate regressions? I'd probably winsorize once overall and run a single regression with interactions of size indicators and your variables? $\endgroup$ – Matthew Gunn Apr 10 '17 at 13:43

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.