Florian Hartig

Hi Lukas, thanks for that, good idea. I honestly can't recall what the reason was to implement a special ecdf, but I suspect my reasoning was that the default R...

In general, feel free to modify this function, I guess a base question though (before coding) is how a sensible ecdf should be defined in this context. p.s.: two other...

@EttnerAndreas - could you have a look at this?

There is at least a simulate function https://rdrr.io/cran/gjam/man/gjamSimData.html

Hi, sorry that it took me so long to get back to you. This concerns something that I had not thought about in detail before, and I wanted to first...

An afterthought / afterexplanation - not sure if this became sufficiently clear in the text above: Even if I manage to do what's promised in https://github.com/florianhartig/DHARMa/issues/38, i.e. stabilize the value...

pps: I realize these doubts kind of contradict my recommendation to run the test a few times. I guess the truth is that I really have to test if there...

Hi, your question 1 this seems to be the same issue as #220, right? About question 2: yes, the pattern seems to come from the bounds on your data, this...

Hi Ben, I will post this to @mfasiolo (developer of qgam), but I don't particularly think that qgam is sensitive to small sample sizes. Matteo, for context, in my presentation...

yes, they do, I calculate the qgam p-values for the 3 quantiles, and then correct for multiple testing, see here https://github.com/florianhartig/DHARMa/blob/5faa7a6d47f9b18f9854d5aba54b4abb603eacd4/DHARMa/R/tests.R#L121 This works excellent btw. and I was very happy...