Hello,
I'm trying to conduct a generalized mixed model analysis (logistic). I do not encounter any error with jamovi. But when I run the same analysis with R, it results in singular fit error. Do you have any suggestions about why this discrepancy might emerge?
I attached the jamovi result. The code that I use in R is below.
glmer(stay ~ transition2*reward2 + (transition2*reward2 + 1|participantno), data=data_mel3, family="binomial")
Thank you,
Anıl Şafak Kaçar
Singular Fit Error in Generalized Mixed Model
Singular Fit Error in Generalized Mixed Model
- Attachments
-
- Capture.JPG (41.09 KiB) Viewed 1836 times
- mcfanda@gmail.com
- Posts: 462
- Joined: Thu Mar 23, 2017 9:24 pm
Re: Singular Fit Error in Generalized Mixed Model
The latest version of glmer() warns you for "near" singular fit when using the default optimizer. GAMLj, when it finds possible singular fit, changes the optimizer to find a better solution. If you do not see a warning in GAMLj, it means it found an optimizer that produced an estimation with no singular fit.
let me know if that does not work for you
let me know if that does not work for you
Re: Singular Fit Error in Generalized Mixed Model
Thank you very much for your quick response. Is there any way to see which optimizer is used by GAMLj?
- mcfanda@gmail.com
- Posts: 462
- Joined: Thu Mar 23, 2017 9:24 pm
Re: Singular Fit Error in Generalized Mixed Model
that's a good question. I'm afraid it does not say it in the output. We can add it as a footnote in the next version. We do try to keep the output clean, so we avoid adding information that is not essential.