Recalibration: a post-processing method for approximate Bayesian computation

DOI10.1016/J.CSDA.2018.04.004zbMATH Open1469.62133arXiv1704.06374OpenAlexW2963668030WikidataQ129885419 ScholiaQ129885419MaRDI QIDQ1663087FDOQ1663087

S. A. Sisson, G. S. Rodrigues, D. Prangle

Publication date: 21 August 2018

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Abstract: A new recalibration post-processing method is presented to improve the quality of the posterior approximation when using Approximate Bayesian Computation (ABC) algorithms. Recalibration may be used in conjunction with existing post-processing methods, such as regression-adjustments. In addition, this work extends and strengthens the links between ABC and indirect inference algorithms, allowing more extensive use of misspecified auxiliary models in the ABC context. The method is illustrated using simulated examples to demonstrate the effects of recalibration under various conditions, and through an application to an analysis of stereological extremes both with and without the use of auxiliary models. Code to implement recalibration post-processing is available in the R package, abctools.

Full work available at URL: https://arxiv.org/abs/1704.06374

zbMATH Keywords

approximate Bayesian computation (ABC)indirect inferencecoverageregression-adjustment

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Applications of statistics in engineering and industry; control charts (62P30)

Cites Work

• Title not available (Why is that?)
• The largest inclusions in a piece of steel
• Extending approximate Bayesian computation methods to high dimensions via a Gaussian copula model
• A comparative review of dimension reduction methods in approximate Bayesian computation
• Bayesian indirect inference using a parametric auxiliary model
• Constructing Summary Statistics for Approximate Bayesian Computation: Semi-Automatic Approximate Bayesian Computation
• Inference for Stereological Extremes
• Expectation Propagation for Likelihood-Free Inference
• New insights into approximate Bayesian computation
• Diagnostic tools for approximate Bayesian computation using the coverage property
• Asymptotics of sums of lognormal random variables with Gaussian copula
• On the Distribution Function and Moments of Power Sums With Log-Normal Components
• Simultaneous adjustment of bias and coverage probabilities for confidence intervals

Cited In (7)

• Model selection and parameter estimation for an improved approximate Bayesian computation sequential Monte Carlo algorithm
• Approximate Bayesian computation using asymptotically normal point estimates
• Calibration procedures for approximate Bayesian credible sets
• Vector operations for accelerating expensive Bayesian computations - a tutorial guide
• An improved approximate Bayesian computation scheme for parameter inference based on a recalibration post-processing method
• Assessment and Adjustment of Approximate Inference Algorithms Using the Law of Total Variance
• Likelihood-free approximate Gibbs sampling

Uses Software

• ABCtoolbox
• abctools
• abcrf

This page was built for publication: Recalibration: a post-processing method for approximate Bayesian computation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663087)