Computationally efficient Bayesian estimation of high-dimensional Archimedean copulas with discrete and mixed margins

DOI10.1007/S11222-018-9846-YzbMATH Open1430.62101arXiv1608.06174OpenAlexW2904297480MaRDI QIDQ2329809FDOQ2329809

Authors: Yanyan Li 

Publication date: 18 October 2019

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Estimating copulas with discrete marginal distributions is challenging, especially in high dimensions, because computing the likelihood contribution of each observation requires evaluating $2^J$ terms, with $J$ the number of discrete variables. Currently, data augmentation methods are used to carry out inference for discrete copula and, in practice, the computation becomes infeasible when $J$ is large. Our article proposes two new fast Bayesian approaches for estimating high dimensional copulas with discrete margins, or a combination of discrete and continuous margins. Both methods are based on recent advances in Bayesian methodology that work with an unbiased estimate of the likelihood rather than the likelihood itself, and our key observation is that we can estimate the likelihood of a discrete copula unbiasedly with much less computation than evaluating the likelihood exactly or with current simulation methods that are based on augmenting the model with latent variables. The first approach builds on the pseudo marginal method that allows Markov chain Monte Carlo simulation from the posterior distribution using only an unbiased estimate of the likelihood. The second approach is based on a Variational Bayes approximation to the posterior and also uses an unbiased estimate of the likelihood. We show that Monte Carlo and randomised quasi Monte Carlo methods can be used with both approaches to reduce the variability of the estimate of the likelihood, and hence enable us to carry out Bayesian inference for high values of $J$ for some classes of copulas where the computation was previously too expensive. Our article also introduces {em a correlated quasi random number pseudo marginal} approach into the literature. The methodology is illustrated through several real and simulated data examples.

Full work available at URL: https://arxiv.org/abs/1608.06174

Recommendations

• Estimating Archimedean copulas in high dimensions
• Likelihood inference for Archimedean copulas in high dimensions under known margins
• Extending approximate Bayesian computation methods to high dimensions via a Gaussian copula model
• A Bayesian semiparametric Archimedean copula
• Approximate Bayesian computation for copula estimation
• Efficient Bayesian inference for Gaussian copula regression models
• Archimedean copula estimation using Bayesian splines smoothing techniques
• Estimation of copula models with discrete margins via Bayesian data augmentation
• Bayesian estimation of Archimedean copula-based SUR quantile models

zbMATH Keywords

Markov chain Monte Carlovariational BayesArchimedean copulacorrelated pseudo-marginal Metropolis-Hastings

Mathematics Subject Classification ID

Bayesian inference (62F15) Monte Carlo methods (65C05) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Estimation in multivariate analysis (62H12)

Cites Work

• Likelihood inference for Archimedean copulas in high dimensions under known margins
• Bayesian Gaussian Copula Factor Models for Mixed Data
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Adaptive optimal scaling of Metropolis-Hastings algorithms using the Robbins-Monro process
• Title not available (Why is that?)
• Pair copula constructions for multivariate discrete data
• The pseudo-marginal approach for efficient Monte Carlo computations
• Efficient Bayesian inference for Gaussian copula regression models
• Explaining variational approximations
• Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator
• A Stochastic Approximation Method
• The correlated pseudomarginal method
• Copula modeling: An introduction for practitioners
• On the efficiency of pseudo-marginal random walk Metropolis algorithms
• Bayesian interference based only on simulated likelihood particle filter analysis of dynamic economic models
• On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
• Sampling Archimedean copulas
• Estimation of copula models with discrete margins via Bayesian data augmentation
• Model selection for discrete regular vine copulas

Cited In (10)

• An algorithm for estimating non-convex volumes and other integrals in \(n\) dimensions
• On the occasional exactness of the distributional transform approximation for direct Gaussian copula models with discrete margins
• Particle methods for stochastic differential equation mixed effects models
• Copulae: an overview and recent developments
• Mixture copulas with discrete margins and their application to imbalanced data
• Estimation of copula models with discrete margins via Bayesian data augmentation
• A mixture of Clayton, Gumbel, and Frank copulas: a complete dependence model
• Variational Bayes Estimation of Discrete-Margined Copula Models With Application to Time Series
• A mixture of regular vines for multiple dependencies
• Estimating Archimedean copulas in high dimensions

Uses Software

• bfa
• tmg

This page was built for publication: Computationally efficient Bayesian estimation of high-dimensional Archimedean copulas with discrete and mixed margins

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2329809)