Using the nlme package in R, I ran a multilevel regression model model with a random intercept and a fixed linear effect of time with REML estimation:

lme(fixed = outcome ~ 1 + day, random = ~ 1 | ID, data = data, method = "REML", na.action = na.exclude)

The p-values for the fixed effects are exactly 0 - not 0.0000 as I've seen before. Does this indicate that something is wrong with my model?


Without seeing the data and the model it is hard to be absolutely sure, but I would think that it just means that the p value is extremely small. We can do a simulation to show this quite easily:

N <- 1000
group <- rep(c(1,2,3,4,5,6,7,8,9,10),100)
x <- seq(1:N)
y <- rnorm(N, 100, 1) + x + group/10 

group <- as.factor(group)
lmm.lme <- lme(fixed = y ~ x, random = ~ 1 | group)

which gives:

Fixed effects: y ~ x 
                Value  Std.Error  DF  t-value p-value
(Intercept) 100.56748 0.11300572 989  889.933       0
x             0.99998 0.00010884 989 9187.745       0

A lot of other functions show <2e-16 for such p values, but not lme apparently.

  • $\begingroup$ Does this answer your question ? If so, please consider marking it as accepted. If not, please let us know why. Thanks ! $\endgroup$ Jul 19 '20 at 4:50

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.