Improving the INLA approach for approximate Bayesian inference for latent Gaussian models
arXiv:1503.07307 · doi:10.1214/15-EJS1092
Abstract
We introduce a new copula-based correction for generalized linear mixed models (GLMMs) within the integrated nested Laplace approximation (INLA) approach for approximate Bayesian inference for latent Gaussian models. While INLA is usually very accurate, some (rather extreme) cases of GLMMs with e.g. binomial or Poisson data have been seen to be problematic. Inaccuracies can occur when there is a very low degree of smoothing or "borrowing strength" within the model, and we have therefore developed a correction aiming to push the boundaries of the applicability of INLA. Our new correction has been implemented as part of the R-INLA package, and adds only negligible computational cost. Empirical evaluations on both real and simulated data indicate that the method works well.
References in corpus (2)
Cited by in corpus (12)
- Latent Gaussian modeling and INLA: A review with focus on space-time applications
- Improved Laplace Approximation for Marginal Likelihoods
- Fast and accurate Bayesian model criticism and conflict diagnostics using R-INLA
- Integrated Nested Laplace Approximations (INLA)
- Bayesian Logistic Regression for Small Areas with Numerous Households
- Bayesian Computing with INLA: A Review
- Penalty parameter selection and asymmetry corrections to Laplace approximations in Bayesian P-splines models
- Sequential Empirical Bayes method for filtering dynamic spatiotemporal processes
- A Statistical Introduction to Template Model Builder: A Flexible Tool for Spatial Modeling
- Fast cross-validation for multi-penalty ridge regression
- An Extended Laplace Approximation Method for Bayesian Inference of Self-Exciting Spatial-Temporal Models of Count Data
- Computing with R-INLA: Accuracy and reproducibility with implications for the analysis of COVID-19 data