sjmisc (version 1.8)

overdisp: Check overdispersion of GL(M)M's

Description

This function checks generalized linear (mixed) models for overdispersion.

Usage

overdisp(x, trafo = NULL)

Arguments

x

Fitted GLMM (merMod-class) or glm model.

trafo

A specification of the alternative, can be numeric or a (positive) function or NULL (the default). See 'Details' in dispersiontest in package AER. Does not apply to merMod objects.

Value

Information on the overdispersion test.

Details

For merMod-objects, this function is based on the code in the DRAFT r-sig-mixed-models FAQ, section How can I deal with overdispersion in GLMMs?. Note that this function only returns an approximate estimate of an overdispersion parameter. For glm's, this function simply wraps the dispersiontest from the AER-package.

References

DRAFT r-sig-mixed-models FAQ

Examples

data(efc)

# response has many zero-counts, poisson models
# might be overdispersed
barplot(table(efc$tot_sc_e))

fit <- glm(tot_sc_e ~ neg_c_7 + e42dep + c160age,
           data = efc, family = poisson)
overdisp(fit)

library(lme4)
efc$e15relat <- to_factor(efc$e15relat)
fit <- glmer(tot_sc_e ~ neg_c_7 + e42dep + c160age + (1 | e15relat),
             data = efc, family = poisson)
overdisp(fit)