Asymptotically Optimal Pointwise and Minimax Quickest Change-point Detection for Dependent Data

TL;DR

This paper establishes the asymptotic optimality of the Shiryaev--Roberts procedure for quickest change-point detection in dependent data models, under general conditions related to the convergence of log-likelihood ratios.

Contribution

It introduces new classes of sequential detection procedures and proves their asymptotic optimality for dependent data, with verifiable conditions for Markov processes.

Findings

Shiryaev--Roberts procedure is asymptotically optimal under general conditions.

Develops tools for verifying convergence conditions in Markov processes.

Applies results to time series models like autoregression and GARCH.

Abstract

We consider the quickest change-point detection problem in pointwise and minimax settings for general dependent data models. Two new classes of sequential detection procedures associated with the maximal "local" probability of a false alarm within a period of some fixed length are introduced. For these classes of detection procedures, we consider two popular risks: the expected positive part of the delay to detection and the conditional delay to detection. Under very general conditions for the observations, we show that the popular Shiryaev--Roberts procedure is asymptotically optimal, as the local probability of false alarm goes to zero, with respect to both these risks pointwise (uniformly for every possible point of change) and in the minimax sense (with respect to maximal over point of change expected detection delays). The conditions are formulated in terms of the rate of convergence in the strong law of large numbers for the log-likelihood ratios between the "change" and "no-change" hypotheses, specifically as a uniform complete convergence of the normalized log-likelihood ratio to a positive and finite number. We also develop tools and a set of sufficient conditions for verification of the uniform complete convergence for a large class of Markov processes. These tools are based on concentration inequalities for functions of Markov processes and the Meyn--Tweedie geometric ergodic theory. Finally, we check these sufficient conditions for a number of challenging examples (time series) frequently arising in applications, such as autoregression, autoregressive GARCH, etc.