Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Indice de Calinski-Harabasz× | Inertie× | |
|---|---|---|
| Domaine | Évaluation de modèles | Évaluation de modèles |
| Famille | MCDM | MCDM |
| Année d'origine≠ | 1974 | 1967 |
| Auteur d'origine≠ | Tadeusz Calinski, Jerzy Harabasz | Stuart Lloyd, James MacQueen |
| Type≠ | Cluster quality metric | Clustering quality metric |
| Source fondatrice≠ | Calinski, T., & Harabasz, J. (1974). A dendrite method for cluster analysis. Communications in Statistics, 3(1), 1-27. DOI ↗ | Lloyd, S. P. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129-137. DOI ↗ |
| Alias | variance ratio criterion, pseudo F-statistic, CH index | WCSS, within-cluster sum of squares, cluster cohesion |
| Apparentées | 5 | 5 |
| Résumé≠ | The Calinski-Harabasz Index, also called the Variance Ratio Criterion, was introduced by Calinski and Harabasz in 1974. It is a metric that measures the ratio of between-cluster variance to within-cluster variance, adjusted for the number of clusters and data points. Higher values indicate better-separated, more compact clusters. | Inertia, also called Within-Cluster Sum of Squares (WCSS), is a measure of cluster cohesion that quantifies how tightly points are grouped around their cluster centroids. Lower values indicate more compact, cohesive clusters. Inertia is the primary objective function for k-means clustering and has been a fundamental metric since the method's introduction. |
| ScholarGateJeu de données ↗ |
|
|