Decomposition of Kendall's τ: implications for clustering
✍ Scribed by T. Kowalczyk; M. Niewiadomska-Bugaj
- Book ID
- 104301396
- Publisher
- Elsevier Science
- Year
- 2000
- Tongue
- English
- Weight
- 119 KB
- Volume
- 48
- Category
- Article
- ISSN
- 0167-7152
No coin nor oath required. For personal study only.
✦ Synopsis
A decomposition of a generalized Kendall's into three components ("within", "between" and "remainder" terms) is presented. We show how the maximization of the "between" term can be used in clustering and that the optimal decomposition in the case of a regular dependence of variables is non-overlapping ( R = 0): Characterization of admissible solutions to maximization problem is provided.
📜 SIMILAR VOLUMES
Several methods of testing general one-sample and two-sample hypotheses of Kendall's r are diecussed. The performance of these procedures in typical situations likely to occur in practioe was investigated by numerou8 Monte Carlo experimenfa The common one-sample feet (610 : T = 0) based on the permu