Abstract
Inference of complex hierarchical models is an increasingly common problem in modern Bayesian data analysis. Unfortunately, there are few computationally efficient and widely applicable methods for selecting between competing hierarchical models. In this paper we adapt ideas from the information theoretic minimum message length principle and propose a powerful yet simple model selection criteria for general hierarchical Bayesian models called MML-h. Computation of this criterion requires only that a set of samples from the posterior distribution be available. The flexibility of this new algorithm is demonstrated by a novel application to state-of-the-art Bayesian hierarchical regression estimation. Simulations show that the MML-h criterion is able to adaptively select between classic ridge regression and sparse horseshoe regression estimators, and the resulting procedure exhibits excellent robustness to the underlying structure of the regression coefficients.
References
Wallace, C.S.: Statistical and Inductive Inference by Minimum Message Length. Information Science and Statistics, 1st edn. Springer, New York (2005)
Wallace, C.S., Freeman, P.R.: Estimation and inference by compact coding. J. R. Stat. Soc. (Ser. B) 49(3), 240–252 (1987)
Carvalho, C.M., Polson, N.G., Scott, J.G.: The horseshoe estimator for sparse signals. Biometrika 97(2), 465–480 (2010)
Makalic, E., Schmidt, D.F.: Minimum message length shrinkage estimation. Stat. Prob. Lett. 79(9), 1155–1161 (2009)
Chib, S.: Marginal likelihood from the Gibbs output. J. Am. Stat. Assoc. 90(432), 1313–1321 (1995)
Lewis, S.M., Raftery, A.E.: Estimating Bayes factors via posterior simulation with the Laplace-Metropolis estimator. J. Am. Stat. Assoc. 92, 648–655 (1997)
Fitzgibbon, L.J., Dowe, D.L., Allison, L.: Univariate polynomial inference by Monte Carlo message length approximation. In: Proceedings of the Nineteenth International Conference on Machine Learning (ICML 2002), pp. 147–154 (2002)
Makalic, E., Schmidt, D.F.: A simple sampler for the horseshoe estimator. IEEE Signal Process. Lett. 23(1), 179–182 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Schmidt, D.F., Makalic, E., Hopper, J.L. (2016). Approximating Message Lengths of Hierarchical Bayesian Models Using Posterior Sampling. In: Kang, B.H., Bai, Q. (eds) AI 2016: Advances in Artificial Intelligence. AI 2016. Lecture Notes in Computer Science(), vol 9992. Springer, Cham. https://doi.org/10.1007/978-3-319-50127-7_41
Download citation
DOI: https://doi.org/10.1007/978-3-319-50127-7_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50126-0
Online ISBN: 978-3-319-50127-7
eBook Packages: Computer ScienceComputer Science (R0)