search

strengejacke / sjstats

Effect size measures and significance tests
https://strengejacke.github.io/sjstats
189 stars 21 forks source link

Tweedie r2 #46

Closed mebrooks closed 5 years ago

mebrooks commented 6 years ago

Would it be possible to calculate an R2 value of models with the Tweedie distribution fit via glmmTMB? I found a worked example using cpglmm in Nakagawa, Johnson, and Schielzeth 2017 Appendix s6. Is there anything particular that is missing from glmmTMB?

mebrooks commented 6 years ago

Sorry, I see now that to replicate the example linked above, glmmTMB needs VarCorr to work for the Tweedie and underlying that is the issue that we need to calculate the variance. I'll work on the variance part for now.

strengejacke commented 5 years ago

I saw you are submitting an update of glmmTMB to CRAN - is this issue addressed (i.e. do you have VarCorr for Tweedie now)?

mebrooks commented 5 years ago

Sorry, we didn't have time yet. I hope to do it in the next few months.

strengejacke commented 5 years ago

Ok, no hurry. Just asking because I'm planning to submit an update in January, and I would have tried to address this issue before submission if this had already gone into glmmTMB.

strengejacke commented 5 years ago

Closing in favor of https://github.com/easystats/insight/issues/68