The Hellinger Correlation
| Autor: | Gery Geenens, Pierre Lafaye de Micheaux |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Statistics and Probability 05 social sciences Mathematics - Statistics Theory Statistics Theory (math.ST) 01 natural sciences Copula (probability theory) k-nearest neighbors algorithm Methodology (stat.ME) Correlation 010104 statistics & probability 0502 economics and business Statistics FOS: Mathematics 0101 mathematics Statistics Probability and Uncertainty Hellinger distance Random variable Statistics - Methodology 050205 econometrics Mathematics |
| Zdroj: | Journal of the American Statistical Association. 117:639-653 |
| ISSN: | 1537-274X 0162-1459 |
| DOI: | 10.1080/01621459.2020.1791132 |
| Popis: | In this paper, the defining properties of a valid measure of the dependence between two random variables are reviewed and complemented with two original ones, shown to be more fundamental than other usual postulates. While other popular choices are proved to violate some of these requirements, a class of dependence measures satisfying all of them is identified. One particular measure, that we call the Hellinger correlation, appears as a natural choice within that class due to both its theoretical and intuitive appeal. A simple and efficient nonparametric estimator for that quantity is proposed. Synthetic and real-data examples finally illustrate the descriptive ability of the measure, which can also be used as test statistic for exact independence testing. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|