Florian Hartig

Hi @ kduskin, I suspect you have only 2 factor levels each for party*feed - DHARMa is per default plotting residuals against the fixed effect (marginal) predictions only. See #43...

@melina-leite given the large number of people that have problems with this, I would see this as priority for the 0.4.8 release! My ideal solution would be to copy the...

Best thing would be to copy more or less the approach taken in https://theoreticalecology.github.io/AdvancedRegressionModels/2C-RandomEffects.html#residual-pattern-per-group You can have a look there how they handle the formula and access the data in...

Hello, thanks for your questions, which I reply to below: 1. Sorry, yes, this was a typo. Corrected 2. This is an interesting idea, and I have to think about...

Hello Baptiste, What your plots tell you is that there is a misfit that is not random. What DHARMa can't tell you is how much impact that has on the...

Hello Batiste, regarding your last question: exactly, I just mean because in the overview plot, you see that the misfit occurred in particular for small predictions, I thought I would...

p.s.: just to re-iterate: DHARMa highlights that deviations are significant, which is something that is not done in standard plot functions, but see my comments in the vignette: significant just...

That's great. Note that a possible explanation for this is that the REs deviate from normality or correlate with predictors, which you could check as well.

Hello, this doesn't look super concerning to me, but it does confirm the point in the vignette that you can have perfectly fine patterns per data point, but once you...

Hi Josh, sorry for the late reply, we were all on holidays. The strong change of the residuals with n is weird, and I suspect that it has something to...