In short, I need to get the importance of the variables after a zero-inflated regression, with all my predictors being dichotomous factors. I tried something like this:

data("bioChemists", package = "pscl")
fm_zip2 <- zeroinfl(art ~ . | ., data = bioChemists)
relImportance <- calc.relimp(fm_zip2, type = "lmg", rela = TRUE)

But I only get error messages, such as that the resulting model must be of the class "glm" or like the following one (from the previous code):

Error in calc.relimp.default.intern(object = list(coefficients = list( : 
If x is NULL, then object must be a data frame or a matrix.

How can I fix this? Thanks!


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.