Approximate Laplace importance sampling for the estimation of expected Shannon information gain in high-dimensional Bayesian design for nonlinear models

DOI10.1007/S11222-022-10159-2zbMath1496.62010OpenAlexW4298144027MaRDI QIDQ2080366

David C. Woods, Timothy W. Waite, Yiolanda Englezou

Publication date: 7 October 2022

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

Full work available at URL: https://doi.org/10.1007/s11222-022-10159-2

zbMATH Keywords

Monte Carloimportance samplingoptimal design

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Optimal statistical designs (62K05)

Uses Software

• Rcpp
• RcppArmadillo
• Stan
• BayesDA
• Julia
• acebayes

Cites Work

• Unnamed Item
• BayesDA
• Julia
• Expected information as ecpected utility
• Bayesian experimental design: A review
• RcppArmadillo: accelerating R with high-performance C++ linear algebra
• An approach for finding fully Bayesian optimal designs using normal-based approximations to loss functions
• A Laplace-based algorithm for Bayesian adaptive design
• Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
• Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
• Monte Carlo and quasi-Monte Carlo sampling
• Julia: A Fresh Approach to Numerical Computing
• On a Measure of the Information Provided by an Experiment
• Computing Bayes Factors by Combining Simulation and Asymptotic Approximations
• Optimal Bayesian Design by Inhomogeneous Markov Chain Simulation
• Locally Optimal Designs for Estimating Parameters

This page was built for publication: Approximate Laplace importance sampling for the estimation of expected Shannon information gain in high-dimensional Bayesian design for nonlinear models