[R-sig-ME] Fwd: help with a cross-classified random effects model code in R.
bates at stat.wisc.edu
Wed Sep 3 14:44:55 CEST 2008
On Wed, Sep 3, 2008 at 7:14 AM, Stijn Ruiter <s.ruiter at maw.ru.nl> wrote:
> Dear Dr. Bates,
> You replied to a question by Violet(Shu) Xu on how to estimate
> cross-classified (XC) models. In the DIGEST version however, no example
> code is provided.
> In general, how do we estimate XC models using lme4?
> Is the following example for a null model for some dependent variable Y
> for pupils who attended specific primary and secondary schools correct?
> Or does lmer then estimate a nested model?
That will estimate the model with crossed random effects. An example
of exactly this type is
> data(ScotsSec, package = "mlmRev")
Loading required package: Matrix
Loading required package: lattice
Attaching package: 'Matrix'
The following object(s) are masked from package:stats :
> (fm1 <- lmer(attain ~ (1|primary) + (1|second), ScotsSec))
Linear mixed model fit by REML
Formula: attain ~ (1 | primary) + (1 | second)
AIC BIC logLik deviance REMLdev
17159 17183 -8575 17149 17151
Groups Name Variance Std.Dev.
primary (Intercept) 1.13002 1.0630
second (Intercept) 0.37222 0.6101
Residual 8.11069 2.8479
Number of obs: 3435, groups: primary, 148; second, 19
Estimate Std. Error t value
(Intercept) 5.5017 0.1787 30.79
To see that the primary and secondary schools classifications are not
nested you can check the image of the cross classification of those
factors produced by
image(xtabs(~ primary + second, ScotsSec, sparse = TRUE))
I enclose a PDF file of that image.
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 59109 bytes
Desc: not available
More information about the R-sig-mixed-models