[R] residuals in lmer

[Douglas Bates]

Jacob Michaelson wrote:
> 
> On Apr 24, 2005, at 11:42 PM, Renaud Lancelot wrote:
> 
>> Jacob Michaelson a écrit :
>>
>>> Does anyone know how to extract residuals in lmer?
>>> Here's the error I get:
>>>  >  
>>> crop.lme=lmer(response~variety*irrigation*pesticide+(1|rep)+(1|rep: 
>>> pesticide)+(1|rep:pesticide:irrigation), crop.data)
>>>  > qqnorm(crop.lme)
>>> Error in qqnorm.default(crop.lme) : y is empty or has only NAs
>>>  > resid(crop.lme)
>>> NULL
>>> Thanks!
>>> --Jake
>>> ______________________________________________
>>> R-help at stat.math.ethz.ch mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> PLEASE do read the posting guide! 
>>> http://www.R-project.org/posting-guide.html
>>
>> I'm afraid they're not (yet) available. At least, you can write a 
>> small function to compute response residuals, using predictions from 
>> the fixed and random parts, built with model.matrix(), fixef() and 
>> ranef(). Let me know if you need an example (I'm not available this 
>> morning).
> 
> 
> 
> Sure, an example would be very helpful, thanks!

Version 0.95-6 of the lme4 package has an lmer method for resid and for 
residuals.