2

I ran the model:

lmer11 <- lmerTest::lmer(duration ~ (1|piece) + (1+color|speaker) + group*color*sex, data=data1.frame, REML=FALSE, na.action=na.omit)

The output is similar to lmer. I do not understand as I run the same syntax structure of other models, and it works fine. Do you have any idea why lmerTest does not give me p-values for this model?

user3288202
  • 313
  • 1
  • 4
  • 14

1 Answers1

2

By default in lmerTest if some error occurs then the output from lme4 is provided. So I guess some computational error has occurred - probably the reason lies in the non-positive definite asymptotic variance-covariance matrix for this model - a reproducible example together with the sessionInfo() would really help!

Alexandra
  • 76
  • 1
  • Hi Alexandra, lmerTest also gives me this: Error in `colnames<-`(`*tmp*`, value = c("Estimate", "Std. Error", "df", : length of 'dimnames' [2] not equal to array extent / I have no idea what this mean. Do you have any idea? – user3288202 Feb 28 '14 at 07:59