0

I have conducted a Mixed linear model in R and in the past, everything went well. But now, there is a weird warning message and I don't know how to fix it. Maybe you have got an idea what I should do next, thanks in advance!

Here is the warning message and my code:

Warning message:

In checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model failed to converge with max|grad| = 4.40085 (tol = 0.002, component 1)

And this is my code:

 cc_full.mod <- glmer(Ergebnis ~ 1 + Risikodarstellung*Icon*Position + (1 |id), 
    data = daten.long, family = binomial,
    control=glmerControl(optimizer="bobyqa"))
allFit(cc_full.mod)
Ben Bolker
  • 211,554
  • 25
  • 370
  • 453
seboe
  • 13
  • 3
  • * Maybe because of misleading random structure? Or due to multi-colinearity? I literally have no clue but if you need further information in order to answer my question, I will post it right here. Thanks! – seboe Aug 11 '23 at 23:38
  • There's almost no chance that we can answer this without a [mcve] (see e.g. https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example ). Did you read the `?troubleshooting` and `?convergence` help pages in the `lme4` package? – Ben Bolker Aug 12 '23 at 00:37
  • Thanks, I will read the ?troubleshooting and ?converge pages first and maybe come back to this question. I´ve read the minimal reproducible example page but I still don*t know what to include. My code is very detailed but has nothing to do with the Mixed linear model (beforehand, I just recode some data for my graphs etc.)... – seboe Aug 12 '23 at 08:48

0 Answers0