paper

An Asymptotically Efficient Metropolis-Hastings Sampler for Bayesian Inference in Large-Scale Educational Measuremen

arXiv:1808.03947

Abstract

This paper discusses a Metropolis-Hastings algorithm developed by \citeA{MarsmanIsing}. The algorithm is derived from first principles, and it is proven that the algorithm becomes more efficient with more data and meets the growing demands of large scale educational measurement.

An Asymptotically Efficient Metropolis-Hastings Sampler for Bayesian Inference in Large-Scale Educational Measuremen · wovepaper