Error in if (REML) p else 0L : the condition has length > 1

Question

I am trying to calculate the null model as follows:

null <- lmer(Binomialvariable ~  1 + (1|ID), data=data, REML=F) 

and I get the following error message:

Error in if (REML) p else 0L : the condition has length > 1

I was wondering if someone knows what's wrong, and how I can fix it. Any help will be much appreciated. Thanks

I have tried to add a control variable instead of the 1 value, which gives the same answer. Then I tried REML = T, or remove REML, which gave another error message: object 'REML' not found

Answer 1

I'm 99% sure that you have assigned a vector of length >1 to F in the global environment.

library(lme4)
F <- c(1,2,3)
null <- lmer(Reaction ~ 1 + (1|Subject), sleepstudy, REML = FALSE)  ## fine
null <- lmer(Reaction ~ 1 + (1|Subject), sleepstudy, REML = F)
## Error in if (REML) p else 0L : the condition has length > 1

Best practices:

• always use FALSE instead of taking the F shortcut
• don't assign values to built-in R objects (F, T, c, t, etc etc etc)