[R-sig-ME] Fwd: same old question - lme4 and p-values

[Simon Blomberg]

On Mon, 2008-04-07 at 17:45 -0700, Jarrett Byrnes wrote:
> On Apr 7, 2008, at 4:46 PM, Simon Blomberg wrote:
> 
> > On Mon, 2008-04-07 at 20:47 +1000, John Maindonald wrote:
> > [ snip ]
> >>
> >> Douglas's mcmcsamp() has advanced the state of the art
> >> for multi-level models, offering an approach that had not
> >> previously been readily available.  It is anyone's guess
> >> where it, and statistics and graphs that it makes readily
> >> possible, will in the course of time fit among styles of
> >> presentation that application area people find helpful.
> >
> > Well, it's been possible to easily implement multi-level models in  
> > BUGS
> > using MCMC for a long time. Would you agree that BUGS is readily
> > available? :-) Doug has made it more convenient for R users, but I'm  
> > not
> > sure it has necessarily advanced the state of the art. Maybe brought R
> > up to speed (but ahead of other software which tends to start with the
> > letter S).
> >
> > Simon.
> >
> 
> 
> But BUGS, JAGS, and their ilk require quite a bit of additional  
> coding. 

And R doesn't? Maybe you use Rcmdr? :-) Also users can specify models in
BUGS using DAGs, if coding is too scary an option.

>  This may not be ideal for a wide variety of users.  This is  
> not to mention the problems of prior specification, etc.  What would  
> be ideal (perhaps for lme4 1.1!) would be a model compiler that would  
> run using rbugs, rjags, or another package such as follows for a  
> random block effect:
> 
> my.model<-lmer(Response ~ Treatment + (1 | Block), data=my.data)
> 
> my.mcmc<-bugsMCMC(my.model)
> 
> Perhaps one could even specify priors and the like, if they wished.   
> One could also use this with R2WinBugs and other great packages that  
> are cropping up out there for Bayesian inference.
> 
> This would also take care of the large additional burden of coding in  
> BUGS, but, does also opens the door wide for mis-use of Bayes.  It's  
> also kind of a pie-in-the-sky, but I can dream.
> 
> -Jarrett
> 
> ----------------------------------------
> Jarrett Byrnes
> Population Biology Graduate Group, UC Davis
> Bodega Marine Lab
> 707-875-1969
> http://www-eve.ucdavis.edu/stachowicz/byrnes.shtml
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
-- 
Simon Blomberg, BSc (Hons), PhD, MAppStat. 
Lecturer and Consultant Statistician 
Faculty of Biological and Chemical Sciences 
The University of Queensland 
St. Lucia Queensland 4072 
Australia
Room 320 Goddard Building (8)
T: +61 7 3365 2506
http://www.uq.edu.au/~uqsblomb
email: S.Blomberg1_at_uq.edu.au

Policies:
1.  I will NOT analyse your data for you.
2.  Your deadline is your problem.

The combination of some data and an aching desire for 
an answer does not ensure that a reasonable answer can 
be extracted from a given body of data. - John Tukey.