Electronic Journal of Statistics
- Electron. J. Statist.
- Volume 13, Number 2 (2019), 2462-2520.
Multiple changepoint detection with partial information on changepoint times
This paper proposes a new minimum description length procedure to detect multiple changepoints in time series data when some times are a priori thought more likely to be changepoints. This scenario arises with temperature time series homogenization pursuits, our focus here. Our Bayesian procedure constructs a natural prior distribution for the situation, and is shown to estimate the changepoint locations consistently, with an optimal convergence rate. Our methods substantially improve changepoint detection power when prior information is available. The methods are also tailored to bivariate data, allowing changes to occur in one or both component series.
Electron. J. Statist., Volume 13, Number 2 (2019), 2462-2520.
Received: November 2017
First available in Project Euclid: 25 July 2019
Permanent link to this document
Digital Object Identifier
Li, Yingbo; Lund, Robert; Hewaarachchi, Anuradha. Multiple changepoint detection with partial information on changepoint times. Electron. J. Statist. 13 (2019), no. 2, 2462--2520. doi:10.1214/19-EJS1568. https://projecteuclid.org/euclid.ejs/1564041629