Single Changepoint Procedures

TL;DR

This paper reviews and unifies the main single changepoint tests used in climate time series analysis, providing asymptotic quantiles and derivations to facilitate detection of mean and trend shifts in climate data.

Contribution

It consolidates prominent changepoint tests, relates them, and offers derivations of their quantiles for broader application in climatology.

Findings

Analysis of SOI and global temperature series demonstrates the techniques.

Unified presentation of tests aids in climate data homogeneity assessment.

Derivations enable application to unconsidered cases.

Abstract

Single changepoint tests have become a staple check for homogeneity of a climate time series, suggesting how climate has changed should non-homogeneity be declared. This paper summarizes the most prominent single changepoint tests used in today's climate literature, relating them to one and other and unifying their presentations. Asymptotic quantiles for the individual tests are presented. Derivations of the quantiles are given, enabling the reader to tackle cases not considered within. Our work here studies both mean and trend shifts, covering the most common settings arising in climatology. SOI and global temperature series are analyzed within to illustrate the techniques.