Approximate Bayesian computation with composite score functions
From MaRDI portal
(Redirected from Publication:294244)
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.
Recommendations
- Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. With discussion and authors' reply
- 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
Cites work
- scientific article; zbMATH DE number 5849508 (Why is no real title available?)
- scientific article; zbMATH DE number 4100431 (Why is no real title available?)
- scientific article; zbMATH DE number 1122119 (Why is no real title available?)
- scientific article; zbMATH DE number 800290 (Why is no real title available?)
- A note on pseudolikelihood constructed from marginal densities
- A spectral representation for max-stable processes
- Adaptive approximate Bayesian computation
- Adjusting composite likelihood ratio statistics
- An adaptive sequential Monte Carlo method for approximate Bayesian computation
- An extended Gaussian max-stable process model for spatial extremes
- Analysis of multivariate probit models
- Applied Asymptotics
- Approximate Bayesian computation: a nonparametric perspective
- Approximate Bayesian computational methods
- Approximate Bayesian computing for spatial extremes
- Asymptotics and the theory of inference
- Bayesian composite marginal likelihoods
- Bayesian indirect inference using a parametric auxiliary model
- Bayesian inference from composite likelihoods, with an application to spatial extremes
- Choice of summary statistic weights in approximate Bayesian computation
- Combined composite likelihood
- Composite likelihood estimation for the Brown-Resnick process
- Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. With discussion and authors' reply
- Empirical and simulated adjustments of composite likelihood ratio statistics
- Encompassing and indirect inference
- Estimating Functions in Indirect Inference
- Estimation of parameters for macroparasite population evolution using approximate Bayesian computation
- Expectation propagation for likelihood-free inference
- Geostatistics of extremes
- Issues and strategies in the selection of composite likelihoods
- Likelihood-based inference for max-stable processes
- Logistic Regression for Correlated Binary Data
- Models for discrete longitudinal data.
- Models for stationary max-stable random fields
- Numerical methods of statistics.
- On composite likelihoods in statistical genetics
- On full efficiency of the maximum composite likelihood estimator
- On spatial extremes: with application to a rainfall problem
- On the likelihood function of Gaussian max-stable processes
- Robust Statistics
- Sequential Monte Carlo without likelihoods
- Spatial modeling of extreme snow depth
- Stationary max-stable fields associated to negative definite functions
- Statistical modeling of spatial extremes
Cited in
(16)- An approximate likelihood perspective on ABC methods
- A quasi likelihood approximation of posterior distributions for likelihood-intractable complex models
- Asymptotic expansion of the posterior based on pairwise likelihood
- Objective Bayesian inference with proper scoring rules
- Approximate Bayesian computation by modelling summary statistics in a quasi-likelihood framework
- Modelling extremes using approximate Bayesian computation
- Robust approximate Bayesian inference
- scientific article; zbMATH DE number 7625191 (Why is no real title available?)
- Pseudo-Likelihoods for Bayesian Inference
- Bayesian inference from composite likelihoods, with an application to spatial extremes
- Weak convergence of posteriors conditional on maximum pseudo-likelihood estimates and implications in ABC
- ABC model selection for spatial extremes models applied to south Australian maximum temperature data
- Bayesian composite marginal likelihoods
- Approximate Bayesian computation: a survey on recent results
- Generalized Bayesian likelihood-free inference
- Approximate Bayesian computing for spatial extremes
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)
