MuMIn (version 1.8.0)

QIC: QIC and Quasi-Likelihood for GEE

Description

Calculate quasi-likelihood under the independence model criterion (QIC) for Generalized Estimating Equations.

Usage

QIC(object, ..., typeR = FALSE)
quasiLik(object, ...)

Arguments

object

a fitted model object of class gee, geepack or yags.

...

for QIC, optionally more fitted model objects.

typeR

whether to calculate QIC(R) rather than QIC(I).

Value

• If just one object is provided, returns a numeric value with the corresponding QIC; if more than one object are provided, returns a data.frame with rows corresponding to the objects and columns representing QIC and QIC$_{u}$.

encoding

utf-8

References

Pan W. (2001) Akaike's Information Criterion in Generalized Estimating Equations. Biometrics 57: 120-125

Hardin W. J., Hilbe, J. M. (2003) Generalized Estimating Equations. CRC Press.

See Also

Methods exist for gee (package gee), geeglm (geepack), and yags (yags). yags and compar.gee from package ape both provide QIC values.

Examples

library(geepack)
data(ohio)

fm1 <- geeglm(resp ~ age * smoke, id = id, data = ohio,
    family = binomial, corstr = "exchangeable", scale.fix = TRUE)
fm2 <- update(fm1, corstr = "ar1")
fm3 <- update(fm1, corstr = "unstructured")

model.sel(fm1, fm2, fm3, rank = QIC)

# same result:
    dredge(fm1, m.min = 3, rank = QIC, varying = list(
    corstr = list("exchangeable", "unstructured", "ar1")
    ))