[R] Calculating the percentage of explained deviance in lmer

willow1980 jianghua.liu at shef.ac.uk
Sat Nov 21 16:49:21 CET 2009


Sorry for making a mistake! It should be,
(m2 at deviance["wrss"]-m1 at deviance["wrss"])/m2 at deviance["wrss"]

willow1980 wrote:
> 
> Hi, Fabio,
> I only have an idea on how to calculate deviance explained by the fixed
> effects. If you remove fixed effects and introduce one null model such as
> m2<-lmer(response-var ~ 1+(1|Site/Area/Transect),family="binomial"). Then,
> (deviance(m2)-deviance(m1))/deviance(m2) will represent deviance explained
> by fixed effects in m1. Hope this makes some sense.
> Best regards,
> Jianghua
> 
> 
> Fabio Bulleri wrote:
>> 
>> Dear all,
>> I am trying to calculate some measure of the amount of variability in the
>> response variable that is explained by a model fitted in lmer 
>> m1<-lmer(response-var ~
>> Condition+(1|Site/Area/Transect),family="binomial") . 
>> I've seen from the literature that the precentage of explained deviance
>> is a common measure. How can I calculate it?
>> Thanks a lot for your help, I hope this is not too shallow.
>> Best
>> Fabio
>> ------------------------------------------------------------------------------
>> Fabio Bulleri, PhD
>> Dipartimento di Biologia
>> Università di Pisa
>> Via A. Volta 6, I-56126, Pisa, Italy
>> Tel. +39 050 2211448
>> Fax +39 050 2211410
>> 	[[alternative HTML version deleted]]
>> 
>> 
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>> 
>> 
> 
> 

-- 
View this message in context: http://old.nabble.com/Calculating-the-percentage-of-explained-deviance-in-lmer-tp26286427p26457755.html
Sent from the R help mailing list archive at Nabble.com.




More information about the R-help mailing list