Open Access
Translator Disclaimer
June 2020 Bayesian Inference in Nonparanormal Graphical Models
Jami J. Mulgrave, Subhashis Ghosal
Bayesian Anal. 15(2): 449-475 (June 2020). DOI: 10.1214/19-BA1159

Abstract

Gaussian graphical models have been used to study intrinsic dependence among several variables, but the Gaussianity assumption may be restrictive in many applications. A nonparanormal graphical model is a semiparametric generalization for continuous variables where it is assumed that the variables follow a Gaussian graphical model only after some unknown smooth monotone transformations on each of them. We consider a Bayesian approach in the nonparanormal graphical model by putting priors on the unknown transformations through a random series based on B-splines where the coefficients are ordered to induce monotonicity. A truncated normal prior leads to partial conjugacy in the model and is useful for posterior simulation using Gibbs sampling. On the underlying precision matrix of the transformed variables, we consider a spike-and-slab prior and use an efficient posterior Gibbs sampling scheme. We use the Bayesian Information Criterion to choose the hyperparameters for the spike-and-slab prior. We present a posterior consistency result on the underlying transformation and the precision matrix. We study the numerical performance of the proposed method through an extensive simulation study and finally apply the proposed method on a real data set.

Citation

Download Citation

Jami J. Mulgrave. Subhashis Ghosal. "Bayesian Inference in Nonparanormal Graphical Models." Bayesian Anal. 15 (2) 449 - 475, June 2020. https://doi.org/10.1214/19-BA1159

Information

Published: June 2020
First available in Project Euclid: 5 June 2019

MathSciNet: MR4078721
Digital Object Identifier: 10.1214/19-BA1159

Subjects:
Primary: 62-09 , 62F15 , 62G05

Keywords: Bayesian inference , continuous shrinkage prior , Gaussian graphical models , nonparanormal , Sparsity

JOURNAL ARTICLE
27 PAGES


SHARE
Vol.15 • No. 2 • June 2020
Back to Top