| Article ID: | iaor20022588 |
| Country: | Brazil |
| Volume: | 21 |
| Issue: | 1 |
| Start Page Number: | 107 |
| End Page Number: | 122 |
| Publication Date: | Jun 2001 |
| Journal: | Pesquisa Operacional |
| Authors: | Kubrusly L.S. |
| Keywords: | statistics: multivariate |
This paper presents a solution to the problem of finding an index number I for ranking a set of n objects, according to criteria defined by a set of m variables. In general, it is necessary to choose a suitable set of variables, and weights for each variable. Cluster Analysis is used for variable selection, and Principal Component Analysis is used to attain weights. Two applications are presented.