Open Access
March 2018 Optimal Gaussian Approximations to the Posterior for Log-Linear Models with Diaconis–Ylvisaker Priors
James Johndrow, Anirban Bhattacharya
Bayesian Anal. 13(1): 201-223 (March 2018). DOI: 10.1214/16-BA1046


In contingency table analysis, sparse data is frequently encountered for even modest numbers of variables, resulting in non-existence of maximum likelihood estimates. A common solution is to obtain regularized estimates of the parameters of a log-linear model. Bayesian methods provide a coherent approach to regularization, but are often computationally intensive. Conjugate priors ease computational demands, but the conjugate Diaconis–Ylvisaker priors for the parameters of log-linear models do not give rise to closed form credible regions, complicating posterior inference. Here we derive the optimal Gaussian approximation to the posterior for log-linear models with Diaconis–Ylvisaker priors, and provide convergence rate and finite-sample bounds for the Kullback–Leibler divergence between the exact posterior and the optimal Gaussian approximation. We demonstrate empirically in simulations and a real data application that the approximation is highly accurate, even for modest sample sizes. We also propose a method for model selection using the approximation. The proposed approximation provides a computationally scalable approach to regularized estimation and approximate Bayesian inference for log-linear models.


Download Citation

James Johndrow. Anirban Bhattacharya. "Optimal Gaussian Approximations to the Posterior for Log-Linear Models with Diaconis–Ylvisaker Priors." Bayesian Anal. 13 (1) 201 - 223, March 2018.


Published: March 2018
First available in Project Euclid: 21 February 2017

zbMATH: 06873724
MathSciNet: MR3737949
Digital Object Identifier: 10.1214/16-BA1046

Keywords: conjugate prior , Contingency table , credible region , Dirichet–Multinomial , Kullback–Leibler divergence , Laplace approximation

Vol.13 • No. 1 • March 2018
Back to Top