Sean Pinkney
@spinkney
I mostly post about probabilistic programming stuff, statistics, and R/Julia/Python (in that order). I'm a volunteer Stan developer and citizen scientist (papers on arxiv). Currently my day job is doing marketing analytics.
Hey, Alexa I do not want the hat below but I will buy one that says IGNORANCE IS STRENGTH WAR IS PEACE FREEDOM IS SLAVERY
I don't know wtf this is but I'm super into matrices so the non-matrix theology is a non-starter for me
First citation for my flexible parameterization of Cholesky factors of correlation matrices (arxiv.org/abs/2405.07286) this is in "Asymptotics for parametric martingale posteriors" by Edwin Fong, Andrew Yiu paper link at arxiv.org/abs/2410.17692.
With my prior and 4 chains, 400 wu, 400 iter, and everything else standard in cmdstanr I get the results back exactly from the simulation!
Wow, wow! I have a nice prior that helps to repel and attract gaussian mixture models for identification in bayesian modeling. Try the following simulation with 4 or more chains and see how crappy it is (even if you set mu to an ordered vector)