Florian Hartig

p.s.: for future reference: if you want to set shrinkage regularisation on parameters, doing this via a Bayesian prior in brms would be an option that wouldn't confuse DHARMa. In...

Ah, OK, I understand. But is this a numeric problem, or just to get the output more clean? If it's just the latter, @emzepeda could simply fit the fixed effect...

Hello Naveranoc, which GLM structure / package are you talking about? If this is about binomial k/n, with weight = n, this should be handled correctly by DHARMa. In general,...

Hi Naveranoc, hmm ... OK, the way I understand it, weights are acting purely on the likelihood in glmmTMB, so if you have 2x the same observation, you could provide...

OK, the problem appears also with older BT versions which were already on CRAN, and it seems it appears only on Windows devel. The exact file name seems stochastic, this...

Hello, yes, I assume that BT will be back on CRAN soon. The package is currently removed because of a new CRAN policy regarding the format of the help #240,...

Hello Julie, OK, the autocorrelation test will just use the numeric value of time, so indeed, you have to take care that you provide time in the order that it...

Hello Javi, regarding 1): to get outliers, you can use the outliers() function, as in ``` library(lme4) testData = createData(sampleSize = 100, overdispersion = 2, family = poisson()) fittedModel

Hello, regarding your questions 1) Pearson residuals in the Poisson will not be normally distributed for low lambda (predicted values). This is well-known and als shown at the start of...

Hello Rui, the likelihood is automatically vectorised in createBayesianSetup, so if you set parallel = T, your likelihood should be automatically parallelised. You should see that several Rsessions are open...