[R-sig-ME] Comparing models with different random effects

[Douglas Bates]

On Fri, Dec 10, 2010 at 8:38 AM, Gang Chen <gangchen6 at gmail.com> wrote:
> Thanks for the help!
>
>> It could make sense if you anova these two models, to find a better one.
>> (1 | Subj) + (1 | Item)
>> (1 | Subj) + (1 | Subj:Item)
>
> These two models have the same number of parameters (and degrees of
> freedom), thus likelihood ration test in anova() would not be
> available. And that is why I was asking whether AIC/BIC is the only
> way to compare the two model.
>
> My second question is still open: I tend to believe that (1 | Subj) is
> nested within (Task | Subj) since the first model has one parameter
> (variance) which can be viewed as multiple variances in the second
> model being constrained as equal, but I would still appreciate it if
> somebody could confirm this.

If you are using "is nested within" to mean "is a submodel of" then
the answer is yes.

>> 2010/12/9 Gang Chen <gangchen6 at gmail.com>
>>>
>>> Suppose that there are multiple task types (Task) and each task type
>>> is represented with a few questions (Item). And all subjects (Subj)
>>> answer the same questions (Item).
>>>
>>> How do I compare a model with (1 | Subj) + (1 | Item) versus one with
>>> (1 | Subj) + (1 | Subj:Item) in lmer()? Through AIC/BIC (assuming the
>>> fixed effect remain the same)? Would it make more sense to consider (1
>>> | Subj) + (1 | Subj:Item) + (1 | Item)?
>>>
>>> Is (1 | Subj) considered as nested within (Task | Subj)?
>>>
>>> Thanks,
>>> Gang
>>>
>>> _______________________________________________
>>> R-sig-mixed-models at r-project.org mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>>
>>
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>