[R-sig-ME] Speed estimation for lmer?

[Doran, Harold]

Choosing the identity link in glmer is the same as a linear model. You
can test for speed using system.time(), but there may be internal code
reasons why one would prefer glmer over lmer, that I don't know. 

> -----Original Message-----
> From: r-sig-mixed-models-bounces at r-project.org 
> [mailto:r-sig-mixed-models-bounces at r-project.org] On Behalf 
> Of Daniel Ezra Johnson
> Sent: Thursday, September 11, 2008 5:07 PM
> To: r-sig-mixed-models at r-project.org
> Subject: Re: [R-sig-ME] Speed estimation for lmer?
> 
> >>  Roughly speaking: lmer and lmer2 aren't (I think) different any 
> >> more, they were different branches of the same software.  
> They should 
> >> both be much faster than lme.  glmer (from lme4) and glmmPQL (from 
> >> nlme) should not be necessary unless you have binomial, 
> Poisson, etc. 
> >> data rather than normally distributed responses.
> >
> > Ben is correct.  There are functions lmer and lmer2 in the current
> > lme4 package but lmer2 is just a stub that turns around and calls 
> > lmer.  If your response y is on a continuous scale then it 
> should be 
> > lmer that you use.
> 
> so if my response is on a continuous scale, is there any 
> difference between
> 
> lmer(y~fixed+(1|random)) and
> glmer(y~fixed+(1|random),family="gaussian") ?
> 
> the output is the same but since reading the above i'm 
> wondering if 'plain' lmer is written to run faster?
> 
> d
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list 
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>