[R-sig-ME] estimated P values

[Greg Snow]

This post:

http://finzi.psych.upenn.edu/R/Rhelp08/archive/156522.html

has some examples that may help.

-- 
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at imail.org
801.408.8111


> -----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 German Garcia
> Sent: Tuesday, March 03, 2009 1:37 PM
> To: r-sig-mixed-models at r-project.org
> Subject: [R-sig-ME] estimated P values
> 
> Hello all listª!!!
> I` am currently comparing generalized linear mixed models in lmer, with
> quasibinomial families. I read some of the discussions on the R-forum
> and it seems
> that the Laplace approximation used in the current version of lmer is
> good. My problem is that in lmer, with quasibinomial families, only
> get t-values but no associated p-values.
> 
> I understood that LRT for testing fixed effects in no good (Bolker et
> al 2008). So, Is there a way to get a reliable p-value for the fixed
> effects?
> 
> 
> In this forum spoke about Wald F test and wald t test, but I don’t know
> how I estimated this test in R software for GLMM analysis. Can anybody
> talk me about this?
>  Thank you so much
> 
> Lic. Germán García Ecología y Conservación de Aves Marinas Departamento
> de Biología, Facultad de Ciencias Exactas y Naturales, Universidad
> Nacional de Mar del Plata - CONICET Funes 3250 (B7602AYJ) Mar del
> Plata, Argentina Tel Oficina: +54 223 4757008
> 
> 
> 
>       Yahoo! Cocina
> Recetas prácticas y comida saludable
> http://ar.mujer.yahoo.com/cocina/
> 	[[alternative HTML version deleted]]