Maximisation de l'association par regroupement de lignes ou de colonnes d'un tableau croisé
The strength of association between the row and column variables in a crosstable varies with the level of aggregation of each variable. In many settings such as the simultaneous discretization of two variables, it is useful to determine the aggregation level that maximizes the association. The main...
সংরক্ষণ করুন:
| প্রকাশিত: | URI:https://journals.openedition.org/msh, |
|---|---|
| প্রধান লেখক: | , , |
| বিন্যাস: | Article ou chapitre numérique |
| ভাষা: | Français |
| প্রকাশিত: |
Mathématiques et sciences humaines
2006
|
| বিষয়গুলি: | |
| অনলাইন ব্যবহার করুন: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |
| সংক্ষিপ্ত: | The strength of association between the row and column variables in a crosstable varies with the level of aggregation of each variable. In many settings such as the simultaneous discretization of two variables, it is useful to determine the aggregation level that maximizes the association. The main association measures with respect to aggregation of rows and columns are studied and permits a heuristic algorithm to (quasi-)maximize the association through aggregation. Simulations carried out to investigate the reliability of the algorithm are presented. |
|---|