Mattan S. Ben-Shachar
Mattan S. Ben-Shachar
@DominiqueMakowski there indeed seems no to be a `brms` method for this function, and using `sensitivity_to_prior.stanreg()` produces an error.
(Also, not sure if the example in the docs will work, given that `brms` uses flat priors by default for fixed effects.)
Seems like a weird thig to have 🤷♂️ (Also looking at the frequentists link, they assume normality? Then why estimate the density?...) This is beyond me pay grade 😅
I'll have to think a bit about which is correct - maybe we can tag Gavin S.? (Not surprising they are the same - the warning says there is zero...
https://twitter.com/mattansb/status/1361939113398726659
Sounds like something for a hackathon.......
I suggest implementing this in `compare_performance()` as `R2_delta` for linear models only (the only ones for which this really makes sense (As for GLMs the total "variance" on the latent...
I was teaching yesterday and I was called out by students "You don't have delta-R2 available??" This is embarrassing guys....
Oops, how did I miss this? Fixed