Approximate Bayesian computation with composite score functions

DOI10.1007/S11222-015-9551-ZzbMATH Open1505.62348arXiv1311.7286OpenAlexW1978556363MaRDI QIDQ294244FDOQ294244

Authors: Erlis Ruli, N. Sartori, Laura Ventura 

Publication date: 10 June 2016

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

Abstract: Both Approximate Bayesian Computation (ABC) and composite likelihood methods are useful for Bayesian and frequentist inference, respectively, when the likelihood function is intractable. We propose to use composite likelihood score functions as summary statistics in ABC in order to obtain accurate approximations to the posterior distribution. This is motivated by the use of the score function of the full likelihood, and extended to general unbiased estimating functions in complex models. Moreover, we show that if the composite score is suitably standardised, the resulting ABC procedure is invariant to reparameterisations and automatically adjusts the curvature of the composite likelihood, and of the corresponding posterior distribution. The method is illustrated through examples with simulated data, and an application to modelling of spatial extreme rainfall data is discussed.

Full work available at URL: https://arxiv.org/abs/1311.7286

Recommendations

• Constructing Summary Statistics for Approximate Bayesian Computation: Semi-Automatic Approximate Bayesian Computation
• Approximate Bayesian computation by modelling summary statistics in a quasi-likelihood framework
• Approximate Bayesian computational methods
• An Introduction to Approximate Bayesian Computation
• Bayesian composite marginal likelihoods

zbMATH Keywords

likelihood-free inferenceunbiased estimating functionpairwise likelihoodcomplex modelcomposite marginal likelihoodtangent exponential model

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Applications of statistics to environmental and related topics (62P12)

Cites Work

• Bayesian inference from composite likelihoods, with an application to spatial extremes
• Title not available (Why is that?)
• Issues and strategies in the selection of composite likelihoods
• Title not available (Why is that?)
• Likelihood-based inference for max-stable processes
• Applied Asymptotics
• Stationary max-stable fields associated to negative definite functions
• A spectral representation for max-stable processes
• Models for stationary max-stable random fields
• On spatial extremes: with application to a rainfall problem
• Bayesian indirect inference using a parametric auxiliary model
• On the likelihood function of Gaussian max-stable processes
• Bayesian composite marginal likelihoods
• Constructing Summary Statistics for Approximate Bayesian Computation: Semi-Automatic Approximate Bayesian Computation
• Approximate Bayesian computation: a nonparametric perspective
• Sequential Monte Carlo without likelihoods
• Numerical methods of statistics.
• Robust Statistics
• Spatial modeling of extreme snow depth
• Approximate Bayesian computational methods
• An extended Gaussian max-stable process model for spatial extremes
• Models for discrete longitudinal data.
• Analysis of multivariate probit models
• Composite likelihood estimation for the Brown-Resnick process
• Statistical modeling of spatial extremes
• A note on pseudolikelihood constructed from marginal densities
• Adaptive approximate Bayesian computation
• Empirical and simulated adjustments of composite likelihood ratio statistics
• Estimation of parameters for macroparasite population evolution using approximate Bayesian computation
• Choice of summary statistic weights in approximate Bayesian computation
• Estimating Functions in Indirect Inference
• Logistic Regression for Correlated Binary Data
• Expectation propagation for likelihood-free inference
• Geostatistics of extremes
• An adaptive sequential Monte Carlo method for approximate Bayesian computation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Asymptotics and the theory of inference
• On full efficiency of the maximum composite likelihood estimator
• On composite likelihoods in statistical genetics
• Adjusting composite likelihood ratio statistics
• Encompassing and indirect inference
• Approximate Bayesian computing for spatial extremes
• Combined composite likelihood

Cited In (16)

• Weak convergence of posteriors conditional on maximum pseudo-likelihood estimates and implications in ABC
• Bayesian composite marginal likelihoods
• Bayesian inference from composite likelihoods, with an application to spatial extremes
• An approximate likelihood perspective on ABC methods
• Pseudo-Likelihoods for Bayesian Inference
• Approximate Bayesian computing for spatial extremes
• Approximate Bayesian computation: a survey on recent results
• Asymptotic expansion of the posterior based on pairwise likelihood
• Generalized Bayesian likelihood-free inference
• Robust approximate Bayesian inference
• ABC model selection for spatial extremes models applied to south Australian maximum temperature data
• A quasi likelihood approximation of posterior distributions for likelihood-intractable complex models
• Objective Bayesian inference with proper scoring rules
• Title not available (Why is that?)
• Modelling extremes using approximate Bayesian computation
• Approximate Bayesian computation by modelling summary statistics in a quasi-likelihood framework

Uses Software

• SpatialExtremes

This page was built for publication: Approximate Bayesian computation with composite score functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q294244)