On robustness of the Shiryaev–Roberts change-point detection procedure under parameter misspecification in the post-change distribution

DOI10.1080/03610918.2015.1039131zbMATH Open1364.62214arXiv1504.04722OpenAlexW2185884875MaRDI QIDQ5267910FDOQ5267910

Grigory Sokolov, Wenyu du, Aleksey S. Polunchenko

Publication date: 13 June 2017

Published in: Communications in Statistics. Simulation and Computation (Search for Journal in Brave)

Abstract: The gist of the quickest change-point detection problem is to detect the presence of a change in the statistical behavior of a series of sequentially made observations, and do so in an optimal detection-speed-vs.-"false-positive"-risk manner. When optimality is understood either in the generalized Bayesian sense or as defined in Shiryaev's multi-cyclic setup, the so-called Shiryaev-Roberts (SR) detection procedure is known to be the "best one can do", provided, however, that the observations' pre- and post-change distributions are both fully specified. We consider a more realistic setup, viz. one where the post-change distribution is assumed known only up to a parameter, so that the latter may be "misspecified". The question of interest is the sensitivity (or robustness) of the otherwise "best" SR procedure with respect to a possible misspecification of the post-change distribution parameter. To answer this question, we provide a case study where, in a specific Gaussian scenario, we allow the SR procedure to be "out of tune" in the way of the post-change distribution parameter, and numerically assess the effect of the "mistuning" on Shiryaev's (multi-cyclic) Stationary Average Detection Delay delivered by the SR procedure. The comprehensive quantitative robustness characterization of the SR procedure obtained in the study can be used to develop the respective theory as well as to provide a rational for practical design of the SR procedure. The overall qualitative conclusion of the study is an expected one: the SR procedure is less (more) robust for less (more) contrast changes and for lower (higher) levels of the false alarm risk.

Full work available at URL: https://arxiv.org/abs/1504.04722

zbMATH Keywords

sequential analysisquality controlShiryaev-Roberts procedurequickest change-point detection

Mathematics Subject Classification ID

Applications of statistics in engineering and industry; control charts (62P30) Sequential statistical analysis (62L10) Numerical methods for integral equations (65R20) Optimal stopping in statistics (62L15)

Cites Work

• Procedures for Reacting to a Change in Distribution
• CONTINUOUS INSPECTION SCHEMES
• Decision theoretic optimality of the cusum procedure
• Optimal detection of a change in distribution
• On Optimum Methods in Quickest Detection Problems
• A diffusion process and its applications to detecting a change in the drift of Brownian motion
• Numerical Comparison of CUSUM and Shiryaev–Roberts Procedures for Detecting Changes in Distributions
• Average run lengths of an optimal method of detecting a change in distribution
• Quickest detection of drift change for Brownian motion in generalized Bayesian and minimax settings
• Comparison of EWMA, CUSUM and Shiryayev-Roberts procedures for detecting a shift in the mean
• State-of-the-art in sequential change-point detection
• Nearly Optimal Change-Point Detection with an Application to Cybersecurity
• State-of-the-Art in Bayesian Changepoint Detection
• An Accurate Method for Determining the Pre-Change Run Length Distribution of the Generalized Shiryaev-Roberts Detection Procedure
• Performance comparison of some likelihood ratio-based statistical surveillance methods

Cited In (5)

• Third-order Asymptotic Optimality of the Generalized Shiryaev--Roberts Changepoint Detection Procedures
• Model misspecification in discrete time Bayesian online change detection
• Robust Wilcoxon‐Type Estimation of Change‐Point Location Under Short‐Range Dependence
• Nonparametric Shiryaev-Roberts change-point detection procedures based on modified empirical likelihood
• Testing randomness online

This page was built for publication: On robustness of the Shiryaev–Roberts change-point detection procedure under parameter misspecification in the post-change distribution

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5267910)