Efficient Posterior Sampling for Bayesian Poisson Regression

DOI10.1080/10618600.2022.2123337arXiv2109.09520OpenAlexW3200476120MaRDI QIDQ6180722FDOQ6180722

Authors: Laura A. M. D'Angelo, Antonio Canale 

Publication date: 22 January 2024

Published in: Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Abstract: Poisson log-linear models are ubiquitous in many applications, and one of the most popular approaches for parametric count regression. In the Bayesian context, however, there are no sufficient specific computational tools for efficient sampling from the posterior distribution of parameters, and standard algorithms, such as random walk Metropolis-Hastings or Hamiltonian Monte Carlo algorithms, are typically used. Herein, we developed an efficient Metropolis-Hastings algorithm and importance sampler to simulate from the posterior distribution of the parameters of Poisson log-linear models under conditional Gaussian priors with superior performance with respect to the state-of-the-art alternatives. The key for both algorithms is the introduction of a proposal density based on a Gaussian approximation of the posterior distribution of parameters. Specifically, our result leverages the negative binomial approximation of the Poisson likelihood and the successful P'olya-gamma data augmentation scheme. Via simulation, we obtained that the time per independent sample of the proposed samplers is competitive with that obtained using the successful Hamiltonian Monte Carlo sampling, with the Metropolis-Hastings showing superior performance in all scenarios considered.

Full work available at URL: https://arxiv.org/abs/2109.09520

zbMATH Keywords

Metropolis-Hastingscount datalog-linear modelshorseshoe priorimportance samplingPólya-gamma

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• The horseshoe estimator for sparse signals
• The Bayesian Lasso
• Bayesian Analysis of Binary and Polychotomous Response Data
• Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
• Auxiliary mixture sampling for parameter-driven models of time series of counts with applications to state space modelling
• The Analysis of Rates Using Poisson Regression Models
• Handbook of Markov Chain Monte Carlo
• Zero-Inflated Poisson Regression, with an Application to Defects in Manufacturing
• Monte Carlo sampling methods using Markov chains and their applications
• Sparsity information and regularization in the horseshoe and other shrinkage priors
• Variational Gaussian approximation for Poisson data
• Title not available (Why is that?)
• Introducing Monte Carlo Methods with R
• Title not available (Why is that?)
• Computationally efficient multivariate spatio-temporal models for high-dimensional count-valued data (with discussion)
• Adaptive posterior contraction rates for the horseshoe
• The least upper bound on the Poisson-negative binomial relative error
• Combining historical data and bookmakers’ odds in modelling football scores

Cited In (1)

• Predicting COVID-19 hospitalisation using a mixture of Bayesian predictive syntheses

This page was built for publication: Efficient Posterior Sampling for Bayesian Poisson Regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6180722)