[R-sig-ME] glmmTMB

[Maira Fatoretto]

Hello,

I am using glmmTMb with binomial family. I chose REML=TRUE because I have
three random effects and I would like to know which is the restriction used
in this estimation in the package.
The REML = TRUE have better estimation than ML in my case.



Thank you.
Best regards.
--
*Maíra Blumer Fatoretto*
Estatística - Universidade Estadual de Campinas- UNICAMP
Mestra em Ciências(Estatística e Experimentação Agronômica) - ESALQ/USP -
Piracicaba - SP
Doutoranda em Estatística e Experimentação Agronômica
Telefone:(19) 988309481
E-mail: ***@gmail.com

[[alternative HTML version deleted]]

[Ben Bolker]

glmmTMB implements REML by treating the fixed effect parameters as
'random variables', i.e. turning on the Laplace approximation
machinery; see http://bbolker.github.io/mixedmodels-misc/glmmFAQ.html#reml-for-glmms
for starting points in the literature.

https://github.com/glmmTMB/glmmTMB/blob/master/glmmTMB/R/glmmTMB.R#L191
On Mon, Oct 29, 2018 at 6:26 AM Maira Fatoretto

Post by Maira Fatoretto
Hello,
I am using glmmTMb with binomial family. I chose REML=TRUE because I have
three random effects and I would like to know which is the restriction used
in this estimation in the package.
The REML = TRUE have better estimation than ML in my case.
Thank you.
Best regards.
--
*Maíra Blumer Fatoretto*
Estatística - Universidade Estadual de Campinas- UNICAMP
Mestra em Ciências(Estatística e Experimentação Agronômica) - ESALQ/USP -
Piracicaba - SP
Doutoranda em Estatística e Experimentação Agronômica
Telefone:(19) 988309481
[[alternative HTML version deleted]]
_______________________________________________
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models