A multiple filter test for the detection of rate changes in renewal processes with varying variance

TL;DR

This paper introduces a multiple filter test for detecting rate changes in renewal processes, particularly applied to neuronal spike trains, improving detection accuracy over single-window methods.

Contribution

It develops a novel multiple filter approach using several moving windows and Gaussian process thresholds to identify change points in nonstationary renewal processes.

Findings

Multiple filtering increases detection probability.

Over 70% of nonstationary spike trains showed different change points with different window sizes.

Application to neuronal data demonstrates practical relevance.

Abstract

Nonstationarity of the event rate is a persistent problem in modeling time series of events, such as neuronal spike trains. Motivated by a variety of patterns in neurophysiological spike train recordings, we define a general class of renewal processes. This class is used to test the null hypothesis of stationary rate versus a wide alternative of renewal processes with finitely many rate changes (change points). Our test extends ideas from the filtered derivative approach by using multiple moving windows simultaneously. To adjust the rejection threshold of the test, we use a Gaussian process, which emerges as the limit of the filtered derivative process. We also develop a multiple filter algorithm, which can be used when the null hypothesis is rejected in order to estimate the number and location of change points. We analyze the benefits of multiple filtering and its increased detection probability as compared to a single window approach. Application to spike trains recorded from dopamine midbrain neurons in anesthetized mice illustrates the relevance of the proposed techniques as preprocessing steps for methods that assume rate stationarity. In over 70% of all analyzed spike trains classified as rate nonstationary, different change points were detected by different window sizes.