Simulation-based inference and approximate Bayesian computation in ecology and population genetics
Paul Kedrosky asks: Have you written anything on approximate Bayesian computation? It is seemingly all the rage in ecology and population genetics, and this recent paper uses it heavily to come to some heretical...
Webinar: An introduction to Bayesian multilevel modeling with brms
This post is by Eric. This Wednesday, at 12 pm ET, Paul Bürkner is stopping by to talk to us about brms. You can register here. Abstract The talk will be about Bayesian multilevel models and their implementation in R using the package brms. We will start with a short introduction to multilevel modeling and to Bayesian statistics in general followed by an introduction to Stan, which is a flexible language for fitting open-ended...
Discuss our new R-hat paper for the journal Bayesian Analysis!
Here’s your opportunity: We welcome public contributions to the Discussion of the manuscript the manuscript Rank-normalization, folding, and localization: An improved R-hat for assessing convergence of MCMC by A. Vehtari, A. Gelman, D. Simpson, B. Carpenter and P. C. Bürkner, which will be featured as a Discussion Paper in the June 2021 issue of the journal. You can find the manuscript in the Advance publication section of the...
The Folk Theorem, revisited
It’s time to review the folk theorem, an old saw on this blog, on the Stan forums, and in all of Andrew’s and my applied modeling. Folk Theorem Andrew uses “folk” in the sense of being folksy as opposed to rigorous. The Folk Theorem of Statistical Computing (Gelman 2008): When you have computational problems, often there’s a problem with your model. Isn’t computation often the culprit? Better samplers like the no-U-turn...
Simulation-based calibration: Two theorems
Throat-clearing OK, not theorems. Conjectures. Actually not even conjectures, because for a conjecture you have to, y’know, conjecture something. Something precise. And I got nothing precise for you. Or, to be more precise, what is precise in this post is not new, and what is new is not precise. Background OK, first for the precise part (which is not new): Simulation-based calibration. You have a computer program to get posterior...
Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond
Charles Margossian, Aki Vehtari, Daniel Simpson, Raj Agrawal write: Gaussian latent variable models are a key class of Bayesian hierarchical models with applications in many fields. Performing Bayesian inference on...
“Model takes many hours to fit and chains don’t converge”: What to do? My advice on first steps.
The above question came up on the Stan forums, and I replied: Hi, just to give some generic advice here, I suggest simulating fake data from your model and then fitting the model and seeing if you can recover the...