Nonparametric test for detecting change in distribution with panel data

TL;DR

This paper introduces a nonparametric CUSUM-based test for detecting monotone changes in the relationship between two processes using panel data, with proven asymptotic properties and validated finite sample performance.

Contribution

It proposes a novel nonparametric test for change detection in panel data relationships, with theoretical derivation and bootstrap validation.

Findings

Asymptotic distribution derived for the test statistic

Bootstrap methods effectively assess finite sample properties

Test successfully detects monotone changes in process relationships

Abstract

This paper considers the problem of comparing two processes with panel data. A nonparametric test is proposed for detecting a monotone change in the link between the two process distributions. The test statistic is of CUSUM type, based on the empirical distribution functions. The asymptotic distribution of the proposed statistic is derived and its finite sample property is examined by bootstrap procedures through Monte Carlo simulations.