The version of lmer based on the supernodal Cholesky factorization,
which we will release real soon, does not crash on this example. It
does give very large estimates of the variances in that model fit, at
least for the simulation that I ran.
It is best if you use set.seed(123454321) (or
Thanks to some help by Doug Bates (and the updated version of the Matrix
package), I've refined my question about fitting nested and non-nested
factors in lmer(). I can get it to work in linear regression but it
crashes in logistic regression. Here's my example:
# set up the predictors