A little more.
As Christopher Ryan points out, as long as the zero-inflation model
is non-trivial (i.e. more complex than a single intercept for the whole
population), there's a pi(i) for every observation i (you could
certainly average the pi(i) values if you wanted, or compute pi for an
Are you referring to the zeroinfl() function in the countreg package? If
so, I think
predict(fm_zinb2, type = "zero", newdata = some.new.data)
will give you pi for each combination of covariate values that you
provide in some.new.data
where pi is the probability to observe a zero from the point
I am running a zero inflated regression using the zeroinfl function similar to
the model below:
fm_zinb2 <- zeroinfl(art ~ . | ., data = bioChemists, dist = "poisson")
summary(fm_zinb2)
I have three questions:
1) How can I obtain a value for the parameter pie, which is the fraction of the
p
3 matches
Mail list logo
