pscl (version 0.5)

predprob: Compute predicted probabilities from fitted models

Description

Compute predicted probabilities from fitted models, optionally at new covariate values

Usage

predprob(obj, ...)

Arguments

obj

fitted model object

...

other arguments

Value

• A matrix of predicted probabilities, each row a vector of predicted probabilities over the range of responses seen in the data (i.e., min(y):max(y)), conditional on the values of covariates.

Details

See documentation for specific methods.

See Also

predprob.glm, predprob.zeroinfl

Examples

data(bioChemists)
zip <- zeroinfl(count=art ~ .,
                x = ~ fem + mar + kid5 + phd + ment,
                z = ~ fem + mar + kid5 + phd + ment,
                dist="poisson",        
                data=bioChemists,trace=TRUE) ## zero-infl poisson
phat <- predprob(zip)

newdata <- expand.grid(list(fem="Men",mar="Married",
                            kid5=1,phd=3.103,
                            ment=0:77))
phat <- predprob(zip,newdata=newdata)