Warnings calculating confidence intervals with mixed models

Question

I'm fairly new to R, but have been running models using lmer. Now I'm trying to calculate the confidence intervals for the intercept and the condition.

For example:

Model1 <- lmer(Response ~ Treatment + 
               (1+Treatment|Hospital), data=Data) 
confint(Model1)

I receive the following output and warnings such as:

              2.5 %     97.5 %
.sig01         5.6742125  6.7891223
.sig02        -0.9234187 -0.5258181
.sig03         2.7687916  8.7684621
.sigma         1.8734195  2.3471127
(Intercept)   26.7283448 28.9332127
TreatmentDrugx 12.1278192 20.4275981

Warning messages: 1: In optwrap(optimizer, par = start, fn = function(x) dd(mkpar(npar1, : convergence code 1 from bobyqa: bobyqa -- maximum number of function > evaluations exceeded

2: In optwrap(optimizer, par = start, fn = function(x) dd(mkpar(npar1, : convergence code 1 from bobyqa: bobyqa -- maximum number of function evaluations exceeded

When I try:

confint(Model1, parm="beta_")

I do not get the warnings but only get the confidence intervals for the intercept and for the level of treatment.

Are these intercepts okay, or should the previous warnings make me wary to accept those as CIs?

Sorry if this is a dumb question, again, do not have to much in depth statistical knowledge or coding experience.

Answer 1

it probably won't make a huge difference, but you should try adding

control=lmerControl(optCtrl=list(maxfun=10000))

to your function arguments.