DHARMa

DHARMa copied to clipboard

florianhartig

Advantage would be that grouping could be calculated on x,y,time automatically Disadvantage is that all is getting a bit more complicated

florianhartig

Heteroskedasticity in residual plot for mgcv::gam with family=nb()

8

A user asks about these residual plots: - If they are acceptable - What one could do to solve the problem > m1.i m1.i m1.i$family$getTheta(TRUE)# > > m1.k1 > ...

florianhartig

Randomized quantile residuals for ordinal models

2

I confused discussions I had with @florianhartig on Twitter and put this into wrong issue, when a new one would have been appropriate. > I think this is sort of...

StaffanBetner

Memory limitations: option to store simulations on disk

3

Addresses #188

dschoenig

securityAssertion("nKcase - wrong dimensions of response") for a simple lme4:lmer linear mixed model

1

Question from a user: > Ich nutze gerade DHARMa (version DHARMa_0.4.1) um ein LMM zu evaluieren (siehe Anhang). > load("Model_nKcase.Rdata") > simOutput.7 plot(simOutput.7)

florianhartig

Unable to calculate quantile regression for quantile 0.25. Possibly to few (unique) data points / predictions.

4

Hi, I am pretty new to DHARMa and model diagnostics in general so please bear with me if I have made a simple correctable error. I am trying to diagnose...

utekleong

Explore questions that emerged in #265

florianhartig

Check weights handling again

1

Should check again that weights are correct handled / errors are thrown for all model types. Specifically: a) for all simulations where weights are correctly included, nothing should happen b)...

florianhartig

Force dispersion tests with re.form = NULL

2

From a bit of testing, it seems that the dispersion test is a lot more sensitive with re.form = NULL, i.e. with conditional simulations. If that is so (to be...

florianhartig