Changepoint detection

Changepoint detection

Allen B. Downey

This page describes my current work in changepoint detection.

Changepoint detection in network measurements


We propose an algorithm for simultaneously detecting and locating changepoints in a time series, and a framework for predicting the distribution of the next point in the series. The kernel of the algorithm is a system of equations that computes, for each index $i$, the probability that the last (most recent) change point occurred at $i$. We evaluate this algorithm by applying it to the change point detection problem and comparing it to the generalized likelihood ratio (GLR) algorithm. We find that our algorithm is as good as GLR, or better, over a wide range of scenarios, and that the advantage increases as the signal-to-noise ratio decreases.


The current version of this paper is available as an unpublished draft in Postscript, gzipped Postscript and PDF.


Here are the slides I used when I presented this work recently.


Coming soon.