Convergence warning

General
1

Hi everyone! I have just started learning statistics and using R, and I am having some difficulties with my models. I have the following nested model which I want to compare using anova():

model_reference <- lmer(frequency ~ group + (1|speaker), my_data, REML = FALSE)
model_1 <- lmer(frequency ~ group + (1+phonemes|speaker), my_data, REML = FALSE)
model_2 <- lmer(frequency ~ group + phonemes + (1|speaker), my_data, REML = FALSE)
model_3 <- lmer(frequency ~ group * phonemes + (1|speaker), my_data, REML = FALSE)

However, after running the models I get these messages which I don't understand.

Warning message:
In as_lmerModLT(model, devfun): Model may not have converged with 1 eigenvalue close to zero: 1.1e-11

or

Warning messages:
1: In checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
Model failed to converge with max|grad| = 0.036393 (tol = 0.002, component 1)
2: In as_lmerModLT(model, devfun) :
Model may not have converged with 1 eigenvalue close to zero: 1.5e-11

Can someone explain what they mean and how I can solve them?

Thank you!

2

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.