Bootstrap Pettitt test for detecting change point in hydroclimatological data: a case study for Itaipu hydroelectric plant in Brazil

TL;DR

This paper introduces a bootstrap version of the Pettitt test for change point detection in hydroclimatological data, demonstrating improved performance over the classical test especially in small samples through simulations and a case study at Itaipu hydroelectric plant.

Contribution

The study develops a bootstrap Pettitt test that enhances change point detection accuracy in small samples, validated by simulations and applied to real hydroclimatological data.

Findings

Bootstrap Pettitt test outperforms classical test in simulations.

Proposed test more effective in small sample scenarios.

Application to Itaipu data confirms improved detection of change points.

Abstract

The Pettitt test has been widely used in climate change and hydrological analyzes. However, studies evidence difficulties of this test in detecting change points, especially in small samples. This study presents a bootstrap application of the Pettitt test, which is numerically compared with the classical Pettitt test by an extensive Monte Carlo simulation study. The proposed test outperforms the classical test in all simulated scenarios. An application of the tests is conducted in the historical series of naturalized flows of the Itaipu Hydroelectric plant in Brazil, where several studies have shown a change point in the 70s. When the series is split into shorter series, to simulate small sample actual situations, the proposed test is more powerful than the classical Pettitt test to detect the change point. The proposed test can be an important tool to detect abrupt changes in water availability, supporting hydroclimatological resources decision making.