In this paper, we present a procedure for scoring and ranking statistical units in ordinal multi-indicator systems, by integrating classical dimensionality reduction tools and novel results in Partial Order Theory. Units are ranked based on “dominance” scores, which depend upon both the structure of the partial order and the joint frequency distribution. Dominance scores are complemented with scores of incomparability among units, so to assess the ranking quality. The procedure is computationally light and is here applied to data about financial literacy in Italy
Ranking extraction in ordinal multi-indicator systems / Fattore, Marco; Arcagni, ALBERTO GIOVANNI. - (2020), pp. 378-383. (Intervento presentato al convegno SIS 2020 tenutosi a Pisa).
Ranking extraction in ordinal multi-indicator systems
Alberto Arcagni
2020
Abstract
In this paper, we present a procedure for scoring and ranking statistical units in ordinal multi-indicator systems, by integrating classical dimensionality reduction tools and novel results in Partial Order Theory. Units are ranked based on “dominance” scores, which depend upon both the structure of the partial order and the joint frequency distribution. Dominance scores are complemented with scores of incomparability among units, so to assess the ranking quality. The procedure is computationally light and is here applied to data about financial literacy in Italy| File | Dimensione | Formato | |
|---|---|---|---|
|
Arcagni_Ranking-extraction_2020.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
412.74 kB
Formato
Adobe PDF
|
412.74 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
