Nonparametric Methods for Multivariate Association Testing

Le résumé fourni par la source

ABSTRACT Understanding the associations between multivariate responses and predictors is a critical challenge in statistics, with significant implications across various applied fields. While several parametric and nonparametric methods exist for univariate analyses, solutions for multivariate settings remain limited and often rely on specific assumptions about the data‐generating model. In this article, we present a comparative analysis of several nonparametric approaches designed to address these limitations. Through an extensive simulation study, we evaluate the performance of these methods, providing insights into their practical applications. To illustrate our findings, we leverage data from the performance of a widely used protein fiber, demonstrating how our proposed methodologies can enhance analysis in complex, real‐world scenarios.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.