> library(MASS) > attach(bacteria) > table(y)y n y 43 177> y<-1*(y=="y") > table(y,trt)trt y placebo drug drug+ 0 12 18 13 1 84 44 49> library(lme4) > model1<-lmer(y~trt+(week|ID),family=binomial,method="PQL")Error in match.arg(method, c("Laplace", "AGQ")) : 'arg' should be one of ?Laplace?, ?AGQ?
<hpdutra <at> yahoo.com> writes:> > > > library(MASS) > > attach(bacteria) > > table(y) > y > n y > 43 177 > > y<-1*(y=="y") > > table(y,trt) > trt > y placebo drug drug+ > 0 12 18 13 > 1 84 44 49 > > library(lme4) > > model1<-lmer(y~trt+(week|ID),family=binomial,method="PQL") > Error in match.arg(method, c("Laplace", "AGQ")) : > 'arg' should be one of ?Laplace?, ?AGQ? >What is your question? Doug Bates warned a few weeks ago that the newer version of lmer would no longer use PQL for GLMMs (he found that it was unreliable, even as a starting method for Laplace fits). I think you can still get the older version if you want it, or you can use glmmPQL from the MASS package (glmmPQL has some advantages anyway). It might be better to forward further discussion to r-sig-mixed. Ben Bolker
I am trying to do an exercise on Crawley's book and I get this error message. I ran the same analysis in the past but now that I upgraded my R in my Macbook I get this message. Is this a bug or what is going on. It doesn't make any sense> library(MASS) > attach(bacteria) > table(y)y n y 43 177> y<-1*(y=="y") > table(y,trt)trt y placebo drug drug+ 0 12 18 13 1 84 44 49> library(lme4) > model1<-lmer(y~trt+(week|ID),family=binomial,method="PQL")Error in match.arg(method, c("Laplace", "AGQ")) : 'arg' should be one of ?Laplace?, ?AGQ? Humberto Dutra