[R-sig-ME] comparing mixed models that share some factors

[Seyed Reza Jafarzadeh]

Hi,

anova(model1, model2) will allow you to compare models with the same
fixed effects, but different specifications of random effects. For
comparing two non-nested models (like your case) you can use AIC or
BIC. Here is a good paper
(http://www.mpi.nl/world/persons/private/baayen/publications/baayenDavidsonBates.pdf)


Reza



On 5/8/07, shabnam shademan <shademan at ucla.edu> wrote:
> Hi all -
>
>
>
> I am unsophisticated user in need of some help.  I have a study in which I
> have two random factors: subject and item.  I also have 3 fixed effects: 1.
> X1 (continuous values), 2. Y (continuous values), and 3. Age (has two levels
> "young" and "old").  My dependent variable is Z.
>
>
>
> I am using the following formula to predict the effect of each factor:
>
> fit1 <- lmer(Z ~Age * X1 * Y + (1 | Subject) + (1 | Stim), method = "ML",
> data = d)
>
>
>
> furthermore, I have the option of using a different model (theoretical, not
> statistical) in order to calculate values for X.  I will call this X2.  This
> means that I could also get a fit in the following way:
>
> fit2 <- lmer(Z ~Age * X2 * Y + (1 | Subject) + (1 | Stim), method = "ML",
> data = d)
>
>
>
>
>
> Here is the question:
>
> Is there anyway to compare fit1 and fit2?  would anova (fit1, fit2) be
> appropriate in this case?  (if possible, would you be kind enough to give me
> references on the answer?)
>
>
>
> Any help is greatly appreciated.
>
> -shabnam
>
>
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>