I have fit a proportional odds model with an ordinal response using Harrell's rms package. Now I want to measure the quality of prediction by computing Somers' D (or a generalized AUC) for this model. I have seen that the rms package has the validate() function to do this, but it operates by resampling. I have out-of-sample data I wish to use. Is there a way to use this data with the rms (or any alternative) package?


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.