[R-sig-ME] Simulating linear mixed models - the Venables approach

Douglas Bates bates at stat.wisc.edu
Mon Apr 7 18:29:50 CEST 2008

In case you missed it on the R-help list, I urge readers of this list
to consider the understated elegance of the code Bill Venables posted
for simulating data from a simple random effects model.

> set.seed(7658943)
> fph <- 0.4
> Sigh <- sqrt(0.0002)
> Sigi <- sqrt(0.04)
> reH <- rnorm(90, fph, Sigh)  ## hospid effects
> dta <- within(expand.grid(hospid = 1:90, empid = 1:80),
           fpi1 <- reH[hospid] + rnorm(7200, fph, Sigi))

One is reminded of John Keats

 'Beauty is truth, truth beauty,—that is all	
 Ye know on earth, and all ye need to know.'

More information about the R-sig-mixed-models mailing list