IRIS PubliCatt
PubliCatt è il repository istituzionale ad accesso aperto dell'Università Cattolica del Sacro Cuore, dove gli utenti autorizzati afferenti all'Ateneo provvedono direttamente e autonomamente a depositare e a rendere visibili le proprie pubblicazioni, inserendo i dati descrittivi del documento stesso ("metadati", quali il titolo, autore, abstract, etc.) e, laddove possibile, il testo della pubblicazione stessa (full-text).
PubliCatt utilizza la piattaforma IRIS (Institutional Research Information System) sviluppata da CINECA.
EnglishComposite indicators (CIs) are important and useful tools in many elds to assess, compare and rank performances, development stage, quality and many other dierent targets. CIs are an overall measure of a multidimen- sional, not directly observable, concept and are obtained by means of a set of manifest variables (elementary indicators) that contribute to dene the over- all measure. In this paper, some matters regarding methods to build CIs are reviewed, assuming elementary indicators are ordinal and quantication is necessary to convert observed data into a numerical form. Scoring methods, aggregating functions and weighting systems are considered. In particular, a scoring method based on the observed distribution or the use of dissim- ilarity indices for quantication together with the Kendall- association or a heterogeneity measure for weighting are suggested. Some of the reviewed procedures are compared using students' satisfaction data.
| Autori: | |
| Titolo: | Some considerations to carry out a composite indicator for ordinal data |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1285/i20705948v8n3p384 |
| Data di pubblicazione: | 2015 |
| Abstract: | Composite indicators (CIs) are important and useful tools in many elds to assess, compare and rank performances, development stage, quality and many other dierent targets. CIs are an overall measure of a multidimen- sional, not directly observable, concept and are obtained by means of a set of manifest variables (elementary indicators) that contribute to dene the over- all measure. In this paper, some matters regarding methods to build CIs are reviewed, assuming elementary indicators are ordinal and quantication is necessary to convert observed data into a numerical form. Scoring methods, aggregating functions and weighting systems are considered. In particular, a scoring method based on the observed distribution or the use of dissim- ilarity indices for quantication together with the Kendall- association or a heterogeneity measure for weighting are suggested. Some of the reviewed procedures are compared using students' satisfaction data. |
| Lingua: | Inglese |
| Rivista: | |
| Citazione: | Zanarotti, M. C., Pagani, L., Some considerations to carry out a composite indicator for ordinal data, <<ELECTRONIC JOURNAL OF APPLIED STATISTICAL ANALYSIS>>, 2015; 2015 (Vol. 08, Issue 03): 384-397. [doi:10.1285/i20705948v8n3p384] [http://hdl.handle.net/10807/78958] |
| Appare nelle tipologie: | Articolo in rivista, Nota a sentenza |
File in questo prodotto:
| File | Descrizione | Tipologia | Note | Licenza | |
|---|---|---|---|---|---|
| eJasa 2015.pdf | Versione Editoriale (PDF) | Nessuna Nota |  | Open Access Visualizza/Apri |
http://hdl.handle.net/10807/78958
Copyright © 2020