Fitting Bayesian item response models in Stata and Stan. (June 2017)

• Record Type: Journal Article
• Authors: Grant, Robert L.; Furr, Daniel C.; Carpenter, Bob; Gelman, Andrew
• Is Part Of: Stata journal. Volume 17:Number 2(2017)
• Page Start: 343
• Page End: 357
• Publication Date: 2017-06
• Subjects: st0477 -- stan -- windowsmonitor -- StataStan -- bayesmh -- Bayesian; Statistics -- Periodicals; Statistics -- Computer programs -- Periodicals; 001.422
• DOI: 10.1177/1536867X1701700206
• Languages: English
• ISSNs: 1536-867X

Abstract

Stata users have access to two easy-to-use implementations of Bayesian inference: Stata's nativebayesmh command and StataStan, which calls the general Bayesian engine, Stan. We compare these implementations on two important models for education research: the Rasch model and the hierarchical Rasch model. StataStan fits a more general range of models than can be fit bybayesmh and uses a superior sampling algorithm, that is, Hamiltonian Monte Carlo using the no-U-turn sampler. Furthermore, StataStan can run in parallel on multiple CPU cores, regardless of the flavor of Stata. Given these advantages and given that Stan is open source and can be run directly from Stata do-files, we recommend that Stata users interested in Bayesian methods consider using StataStan.