Comparison between pystan and numpyro in Bayesian item response theory: evaluation of agreement of estimated latent parameters and sampling performance

Purpose The purpose of this study is to compare two libraries dedicated to the Markov chain Monte Carlo method: pystan and numpyro. In the comparison, we mainly focused on the agreement of estimated latent parameters and the performance of sampling using the Markov chain Monte Carlo method in Bayesi...

Full description

Bibliographic Details

Published in:	PeerJ Computer Science
Main Authors:	Mizuho Nishio, Eiji Ota, Hidetoshi Matsuo, Takaaki Matsunaga, Aki Miyazaki, Takamichi Murakami
Format:	Article
Language:	English
Published:	PeerJ Inc. 2023-10-01
Subjects:	Item response theory Markov chain Monte Carlo Graphics processing unit
Online Access:	https://peerj.com/articles/cs-1620.pdf