I want to run a binary logistic regression and I guess some variables have nonlinearities. So I want to use splines method to understand affect of each range in a continuous variable. When I 'guess' that nonlinearities it will enough to using splines method or I should run a 'test' on variables?

  • $\begingroup$ See stats.stackexchange.com/questions/122212/…. I don't think you should be running any tests! $\endgroup$ Feb 19 at 3:20
  • $\begingroup$ Thank you so much. $\endgroup$ Feb 19 at 3:28
  • $\begingroup$ Is this a good method if I run binary logistic regression for each continuous variable WITH and WITHOUT splines, then I compare their AIC and WALD p-values, and then determine if it's better to use the splines method or not? $\endgroup$ Feb 19 at 22:08


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.