I consider a proportional odds (ordinal regression) model, as described in Agresti (2002) and estimated by R base package function MASS. The software reports t-values but no p-values in summary. I wonder how I should determine the degrees of freedom for the t-test. In simple linear regression $df=n-2$ where $n$ the sample size. Is this also the case for ordinal linear regression?

  • $\begingroup$ Why not extract the residual df from the object? And I think polr is in MASS not base. $\endgroup$
    – mdewey
    Aug 25 '16 at 14:39
  • $\begingroup$ Are you sure residual df is the correct df for the t-test? $\endgroup$
    – tomka
    Aug 25 '16 at 15:13

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.