I am looking for pointers as to what would be the non-parametric equivalent of Nadaraya-Watson regression when modelling a binary outcome. I have been googling and ended up with Generalized Additive Models, but I think these impose functional forms?

  • $\begingroup$ "Nonparametric" has a pretty loose definition, but isn't Nadaraya-Watson already considered nonparametric? $\endgroup$ – Dave Apr 6 at 17:18
  • $\begingroup$ @Dave, thanks for the reply. Yes, NW is non-parametric, but not suited for binary outcomes. That's why I asked what would be the binary outcome alternative. $\endgroup$ – Papayapap Apr 6 at 17:22

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.