Florian Hartig

Hi Björn, > can it be used to identify outliers (e.g. data points with strong influence) similarly to Cook's Distance, so that a non-significant test states that there is no...

I have added a function to return outliers to the development version of DHARMa. In the help, I give a few more hints about the things that I discuss here

Hi Staffan, thanks for the link, interesting! Skimming the paper, it seemed to me that this (conditional) surrogate distribution they use is somehow different to the DHARMa approach where the...

Hi michielvdglind, if you're changing to negBin and you don't get a significant result any more, you must be scratching significance anyway, so this would make me hesitant to trust...

Hi Lukas, thanks for these comments, this is very helpful! If I may summarise my current thinking about this issue, in the light of these comments: * The test glmmFAQ.html...

Hi Lukas, thanks for that, super helpful. I'm curious what @bbolker thinks about that?

Hi Lukas, sorry for the late reply, I am currently a bit overwhelmed with work. Thanks so much for the thoughts! I agree with (and was aware about) issue 2,...

Hi Lukas, OK, thanks for your email, will respond to you in a sek, but wanted to first recapitulate where we are here. I have read through this again, here...

So, this is all saying: I think it's a good idea to try defining a dispersion test that uses the simulated dispersion per data point as a reference. What I...

Here some further thoughts. ``` library(DHARMa) testData = createData(sampleSize = 200, fixedEffects = 1, family = poisson(), randomEffectVariance = 0) fittedModel