Assessing Normality for Mixed Models

Hi Jacob,

You should do similar normality check as you would do for linear 
models, I usually use the qqplot, you can use qqnorm(resid(model)) and 
qqline(resid(model)). Then another assumptions from linear mixed 
models is that the random effect are normally distributed with a mean 
of 0, you can use qqnorm(unlist(ranef(model))) and 
qqline(unlist(ranef(model))) if you have only one random term.

So two things should be normally distributed in linear mixed models: 
the residuals and the random effects.

When you have a low number of level in the random effects normality 
will in some case not be reached just due to the small number of 
levels, I am not aware of ways to account for this, I would either 
include the random effect as fixed effect or use simulation.

Sincerely yours,
Lionel


On 20/05/2014 20:59, AvianResearchDivision wrote:

Hi All,

After doing some extensive googling, searching for ways to assess 
normality
for linear mixed models, I can honestly say my head is swimming in
different proposed techniques that may or may not be valid. Also, when
reading the literature, I find that few studies that use linear mixed
models and random regression actually explicitly address how they assess
normality.  What are the rules with normality with mixed models (if 
there
are any) and what are your techniques to assess normality?  Any input 
that
you can provide would be great and hopefully we help to settle my 
mind on
this issue.

Thank you,
Jacob

    [[alternative HTML version deleted]]