QIC and QICu for GEE
Calculate quasi-likelihood under the independence model criterion (QIC) and QICu based on GEE.
QIC.gee(object)
object |
a fitted model object of class |
Return a vector of QIC, QICu and Quasi-likelihood.
QIC can be used to select the best correlation structure and the best fitting model in GEE analyses. The GEE is fitted by geeglm (geepack). QICu is a simplified version of QIC, which can not be applied to select the optimal working correlation structure. geeglm (geepack) only works for complete data. Thus if there are NA’s in data, the missing values are automatically removed by na.omit.
Cong Xu, Zheng Li and Ming Wang
Liang, K.Y. and Zeger, S.L., 1986. Longitudinal data analysis using generalized linear models. Biometrika, pp.13-22.
Pan, W., 2001. Akaike's information criterion in generalized estimating equations. Biometrics, 57(1), pp.120-125.
Prentice, R.L. and Zhao, L.P., 1991. Estimating equations for parameters in means and covariances of multivariate discrete and continuous responses. Biometrics, pp.825-839.
geeglm (geepack). MuMIn also provides QIC value.
data(imps)
fit <- wgee(Y ~ Drug+Sex+Time, data=imps, id=imps$ID, family="binomial",
corstr="exchangeable")
QIC.gee(fit)
data(seizure)
###reshapre the seizure data to "long" format
seiz.long <- reshape(seizure, varying=list(c("base","y1", "y2", "y3", "y4")),
v.names="y", times=0:4, direction="long")
seiz.long <- seiz.long[order(seiz.long$id, seiz.long$time),]
fit <- wgee(y ~ age + trt + time, data=seiz.long, id=seiz.long$id,
family="poisson", corstr="independence")
QIC.gee(fit)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.