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.

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]

Some considerations to carry out a composite indicator for ordinal data

Zanarotti, Maria Chiara
Primo
;
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.
Inglese
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]
File in questo prodotto:
File Dimensione Formato  
eJasa 2015.pdf

accesso aperto

Tipologia file ?: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 430.56 kB
Formato Adobe PDF
430.56 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/78958
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact