Got overdispersion? Try observation-level random effects with the Poisson-lognormal mixture

What? One of Tristan Mahr’s recent Twitter threads almost broke my brain. wait when people talk about treating overdispersion by using random effects, they sometimes put a random intercept on each row?

Bayesian power analysis: Part III.a. Counts are special.

Version 1.1.0 Edited on April 21, 2021, to remove the broom::tidy() portion of the workflow. Orientation So far we’ve covered Bayesian power simulations from both a null hypothesis orientation (see part I) and a parameter width perspective (see part II).