Bayesian sensitivity analysis with the Fisher-Rao metric

DOI10.1093/BIOMET/ASV026zbMATH Open1452.62252arXiv1403.5150OpenAlexW1911749844MaRDI QIDQ3455809FDOQ3455809

Authors: Sebastian Kurtek, Karthik Bharath 

Publication date: 11 December 2015

Published in: Biometrika (Search for Journal in Brave)

Abstract: We propose a geometric framework to assess sensitivity of Bayesian procedures to modeling assumptions based on the nonparametric Fisher-Rao metric. While the framework is general in spirit, the focus of this article is restricted to metric-based diagnosis under two settings: assessing local and global robustness in Bayesian procedures to perturbations of the likelihood and prior, and identification of influential observations. The approach is based on the square-root representation of densities which enables one to compute geodesics and geodesic distances in analytical form, facilitating the definition of naturally calibrated local and global discrepancy measures. An important feature of our approach is the definition of a geometric $epsilon$-contamination class of sampling distributions and priors via intrinsic analysis on the space of probability density functions. We showcase the applicability of our framework on several simulated toy datasets as well as in real data settings for generalized mixed effects models, directional data and shape data.

Full work available at URL: https://arxiv.org/abs/1403.5150

Recommendations

• Geometric sensitivity measures for Bayesian nonparametric density estimation models
• Bayesian influence analysis: a geometric approach
• scientific article; zbMATH DE number 946667
• A note on the geometry of Bayesian global and local robustness
• Bayesian robustness for multiparameter problems

zbMATH Keywords

geodesicRiemannian manifoldFisher-Rao metricinfluence analysisgeometric \(\epsilon\)-contamination

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric robustness (62G35) Statistics on manifolds (62R30)

Cited In (13)

• Geometric framework for statistical analysis of eye tracking heat maps, with application to a tobacco waterpipe study
• Logistic regression models for elastic shape of curves based on tangent representations
• A geometric variational approach to Bayesian inference
• Elastic functional principal component regression
• On the geometry of Bayesian inference
• Bayesian influence analysis: a geometric approach
• Detecting and diagnosing prior and likelihood sensitivity with power-scaling
• A geometric approach for computing tolerance bounds for elastic functional data
• RADIOHEAD: radiogenomic analysis incorporating tumor heterogeneity in imaging through densities
• Optimal square-root pooling from expert opinions
• A unified approach for outliers and influential data detection: the value of information in retrospect
• Geometric sensitivity measures for Bayesian nonparametric density estimation models
• Sensitivity of Bayes Estimators to Hyper-Parameters with an Application to Maximum Yield from Fisheries

This page was built for publication: Bayesian sensitivity analysis with the Fisher-Rao metric

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3455809)