Approximate Cross-Validated Mean Estimates for Bayesian Hierarchical Regression Models
Open Access
- 14 November 2024
- journal article
- research article
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 34 (2) , 488-497
Abstract
We introduce a novel procedure for obtaining cross-validated predictive estimates for Bayesian hierarchical regression models (BHRMs). BHRMs are popular for modeling complex dependence structures (e.g., Gaussian processes and Gaussian Markov random fields) but can be computationally expensive to run. Cross-validation (CV) is, therefore, not a common practice to evaluate the predictive performance of BHRMs. Our method circumvents the need to rerun computationally costly estimation methods for each cross-validation fold and makes CV more feasible for large BHRMs. We shift the CV problem from probability-based sampling to a familiar and straightforward optimization problem by conditioning on the variance-covariance parameters. Our approximation applies to leave-one-out CV and leave-one-cluster-out CV, the latter of which is more appropriate for models with complex dependencies. In many cases, this produces estimates equivalent to full CV. We provide theoretical results, demonstrate the efficacy of our method on publicly available data and in simulations, and compare the model performance with several competing methods for CV approximation. Code and other supplementary materials available online.Keywords
Funding Information
- National Institutes of Health (R56AI120812-01A1)
- National Institutes of Health (R01AI136664)
- National Institutes of Health (R01AI170249)
- National Institutes of Health (R01HL158963)
This publication has 21 references indexed in Scilit:
- Bayesian Comparison of Latent Variable Models: Conditional Versus Marginal LikelihoodsPsychometrika, 2019
- Speeding Up MCMC by Efficient Data SubsamplingJournal of the American Statistical Association, 2018
- Approximating cross-validatory predictive evaluation in Bayesian latent variable models with integrated IS and WAICStatistics and Computing, 2015
- Approximate Bayesian Inference for Latent Gaussian models by using Integrated Nested Laplace ApproximationsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2009
- Approximate cross‐validatory predictive checks in disease mapping modelsStatistics in Medicine, 2003
- Approximate Inference in Generalized Linear Mixed ModelsJournal of the American Statistical Association, 1993
- Model Determination using Predictive Distributions with Implementation via Sampling-Based Methods1992
- Approximate Bayesian Inference in Conditionally Independent Hierarchical Models (Parametric Empirical Bayes Models)Journal of the American Statistical Association, 1989
- Maximum Likelihood Approaches to Variance Component Estimation and to Related ProblemsJournal of the American Statistical Association, 1977
- Robust regression using iteratively reweighted least-squaresCommunications in Statistics - Theory and Methods, 1977