R help - Apr 2005 - lmer question

Hi --

I'm using lmer for binomial data. I am trying to
replicate estimates provided by Agresti (2002,
Categorical data analysis, Wiley) using abortion data
in table 10.13 (estimates provided in table 12.3 p.
505). 

I fit the same model using these three commands:

a1 <- lmer(resp ~ sex + option1 + option2 + (1|id),
data=abort,family=binomial, method = c("AGQ"))

a2 <- lmer(resp ~ sex + option1 + option2 + (1|id),
data=abort,family=binomial, method = c("Laplace"))

a3 <- lmer(resp ~ sex + option1 + option2 + (1|id),
data=abort,family=binomial, method = c("PQL"))

All three methods provide the exact same estimates
(which should not be the case), and the estimates are
incorrect. I know the data are correctly entered
because I obtain correct estimates with gllamm in
Stata.

I am I doing something wrong here in my commands, or
is the lmer module not implementing AGQ and Laplace
properly with this version?

Markus Bean wrote:
> Hi --
> 
> I'm using lmer for binomial data. I am trying to
> replicate estimates provided by Agresti (2002,
> Categorical data analysis, Wiley) using abortion data
> in table 10.13 (estimates provided in table 12.3 p.
> 505). 
> 
> I fit the same model using these three commands:
> 
> a1 <- lmer(resp ~ sex + option1 + option2 + (1|id),
> data=abort,family=binomial, method = c("AGQ"))
> 
> a2 <- lmer(resp ~ sex + option1 + option2 + (1|id),
> data=abort,family=binomial, method = c("Laplace"))
> 
> a3 <- lmer(resp ~ sex + option1 + option2 + (1|id),
> data=abort,family=binomial, method = c("PQL"))
> 
> All three methods provide the exact same estimates
> (which should not be the case), and the estimates are
> incorrect. I know the data are correctly entered
> because I obtain correct estimates with gllamm in
> Stata.
> 
> I am I doing something wrong here in my commands, or
> is the lmer module not implementing AGQ and Laplace
> properly with this version?
The latter.  Actually it is not implementing them at all in this 
version.  I will upload a new release of the lme4 package later this 
week and insert appropriate messages.