I have calculated a zero-truncated negative-binomial model using glmmadmb, and also vglm, in R. I need to report some measure of goodness of fit for this model. I have already done cross validation (training-test sets), but would like to report another goodness of fit measure too. For a logistic regression I would report % deviance explained, or a pseudo r-squared. Are there similar tests for a zero-truncated negative-binomial model? The R functions do not report deviance, and I am not sure how to calculate it.


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.