[R] LMER

Daniel Malter daniel at umd.edu
Fri Feb 15 01:50:46 CET 2008


Hi,

I run the following models: 

1a. lmer(Y~X+(1|Subject),family=binomial(link="logit")) and
1b. lmer(Y~X+(1|Subject),family=binomial(link="logit"),method="PQL")

Why does 1b produce results different from 1a? The reason why I am asking is
that the help states that "PQL" is the default of GLMMs

and

2. gamm(Y~X,family=binomial(link="logit"),random=list(Subject=~1))

The interesting thing about the example below is, that gamm is also supposed
to fit by "PQL". Interestingly, however, the GAMM fit yields about the
coefficient estimates of 1b. But the significance values of 1a. Any insight
would be greatly appreciated.


library(lme4)
library(mgcv)

Y=c(0,1,1,1,1,0,0,0,0,0,1,1,1,1,0,0,0,1,1,1,1)
X=c(1,2,3,4,3,1,0,0,2,3,3,2,4,3,2,1,1,3,4,2,3)
Subject=as.factor(c(1,2,3,4,5,6,7,1,2,3,4,5,6,7,1,2,3,4,5,6,7))
cbind(Y,X,Subject)

r1=lmer(Y~X+(1|Subject),family=binomial(link="logit"))
summary(r1)

r2=lmer(Y~X+(1|Subject),family=binomial(link="logit"),method="PQL")
summary(r2)

r3=gamm(Y~X,family=binomial(link="logit"),random=list(Subject=~1))
summary(r3$gam)



-------------------------
cuncta stricte discussurus



More information about the R-help mailing list