conditional variances via ranef when multiple terms per factor

[sjPlot]

Maybe this one is related to this issue, but I'm not sure whether it is not implemented yet or in general not possible to calculate?

library(lme4)
library(arm)
data("sleepstudy")
# Uncorrelated RE - Error
fm1 <- lmer(Reaction ~ Days + (1 | Subject) + (0 + Days|Subject), data = sleepstudy)
ranef(fm1, condVar = TRUE)

Warnmeldung:
In ranef.merMod(fm1, condVar = TRUE) :
conditional variances not currently available via ranef when there are multiple terms per factor

[bbolker]

Don't know offhand, although I suspect it's an annoying bookkeeping problem rather than a fundamental theoretical/computational difficulty. There are, unfortunately, several issues in this category ("not fundamentally impossible but would require a significant investment that's not very likely to happen in the absence of a really strong incentive"), such as implementing Gauss-Hermite quadrature for vector-valued random effects (#123) ...