Generalized Measures of Correlation for Asymmetry, Nonlinearity, and Beyond: Some Antecedents on Causality

• 成果类型: Article
• 署名作者: Allen, David E.; McAleer, Michael
• 署名单位: University of Sydney; Asia University Taiwan; Edith Cowan University; Asia University Taiwan; University of Sydney; Erasmus University Rotterdam - Excl Erasmus MC; Erasmus University Rotterdam; Complutense University of Madrid; Complutense University of Madrid; University of Canterbury; Yokohama National University
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2020.1768101
• 发表日期: 2022
• 页码: 214-224
• 关键词: least-squares; dependence; regression; statistics; variables; models

摘要

This note comments on the generalized measure of correlation (GMC) that was suggested by Zheng, Shi, and Zhang. The GMC concept was partly anticipated in some publications over 100 years earlier by Yule in the Proceedings of the Royal Society, and by Kendall. Other antecedents discussed include work on dependency by Renyi and Doksum and Samarov, together with the Yule-Simpson paradox. The GMC metric partly extends the concept of Granger causality, so that we consider causality, graphical analysis and alternative measures of dependency provided by copulas.