Sean Pinkney
@spinkney.bsky.social
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.
I don't know wtf this is but I'm super into matrices so the non-matrix theology is a non-starter for me
February 17, 2025 at 6:08 PM
I don't know wtf this is but I'm super into matrices so the non-matrix theology is a non-starter for me
"Painting to be stepped on." Do not step on the painting!
January 2, 2025 at 9:26 PM
"Painting to be stepped on." Do not step on the painting!
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.
November 29, 2024 at 5:31 PM
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.
Statisticians being based
October 28, 2024 at 10:39 AM
Statisticians being based
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!
September 23, 2024 at 5:20 PM
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)
Try the following simulation with 4 or more chains and see how crappy it is (even if you set mu to an ordered vector)
September 23, 2024 at 5:16 PM
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)
Try the following simulation with 4 or more chains and see how crappy it is (even if you set mu to an ordered vector)
When you troll frequentists on LinkedIn
September 18, 2024 at 11:14 PM
When you troll frequentists on LinkedIn