A one-way ANOVA test for functional data with graphical interpretation

TL;DR

This paper introduces a novel one-way functional ANOVA test with a graphical interpretation, allowing for identification of specific domains responsible for differences among groups, applicable to multidimensional functional data.

Contribution

It extends the global envelope test to functional data, providing a visual tool and post-hoc analysis for group comparisons, including multidimensional cases.

Findings

The test successfully identified differences in fiscal decentralization among European countries.

Graphical interpretation helped locate specific function domains responsible for group differences.

Method demonstrated effective application in analyzing government expenditure decentralization.

Abstract

A new functional ANOVA test, with a graphical interpretation of the result, is presented. The test is an extension of the global envelope test introduced by Myllymaki et al. (2017, Global envelope tests for spatial processes, J. R. Statist. Soc. B 79, 381--404, doi: 10.1111/rssb.12172). The graphical interpretation is realized by a global envelope which is drawn jointly for all samples of functions. If a mean function computed from the empirical data is out of the given envelope, the null hypothesis is rejected with the predetermined significance level $\alpha$. The advantages of the proposed one-way functional ANOVA are that it identifies the domains of the functions which are responsible for the potential rejection. We introduce two versions of this test: the first gives a graphical interpretation of the test results in the original space of the functions and the second immediately offers a post-hoc test by identifying the significant pair-wise differences between groups. The proposed tests rely on discretization of the functions, therefore the tests are also applicable in the multidimensional ANOVA problem. In the empirical part of the article, we demonstrate the use of the method by analyzing fiscal decentralization in European countries. The aim of the empirical analysis is to capture differences between the levels of government expenditure decentralization ratio among different groups of European countries. The idea behind, based on the existing literature, is straightforward: countries with a longer European integration history are supposed to decentralize more of their government expenditure. We use the government expenditure centralization ratios of 29 European Union and EFTA countries in period from 1995 to 2016 sorted into three groups according to the presumed level of European economic and political integration.