[R-sig-ME] Inconsistency: works with CRAN, not with r-forge

[Dieter Menne]

The following example by Michael Kubovy and using Gregory Warnes' gmodels works
with the CRAN version, but not with the current r-forge version lme4
0.999375-13. While it might be caused by some problem in <estimable>, it looks
more like a coef() infelicity to me.

The usual: Cetero censeo estimable in lme/lmer esse.

Dieter

library(lme4)
library(gmodels)
recall <- c(10, 13, 13, 6, 8, 8, 11, 14, 14, 22, 23, 25, 16, 18, 20, 15, 17, 17,
1, 1, 4, 12, 15, 17, 9, 12, 12, 8, 9, 12) 
fr <- data.frame(rcl = recall, time = factor(rep(c(1, 2, 5), 10)), subj =
factor(rep(1:10, each = 3))) 
(fr.lmer <- lmer(rcl ~ time -1 +(1 | subj), fr)) 
mm <- unique(model.matrix(~ time -1, fr)) 
cm <- mm[1, ] - mm[3, ]
cm1 <- mm[1, ] - mm[2, ]
estimable(fr.lmer, cm = cm, conf.into = 0.95) 
estimable(fr.lmer, cm = cm1, conf.into = 0.95)



Error in coef(obj) : unable to align random and fixed effects

traceback()
8: stop("unable to align random and fixed effects")
7: coef(obj)
6: coef(obj)
5: .to.est(obj, cm)
4: as.vector(data)
3: matrix(.to.est(obj, cm), nrow = 1)
2: estimable.default(fr.lmer, cm = cm1, conf.into = 0.95)
1: estimable(fr.lmer, cm = cm1, conf.into = 0.95)