The fuzzy set approach to multidimensional poverty measurement is enjoying increasing popularity. A different, yet strongly related issue concerns geo-informatics surveillance for poverty hot-spot detection: hot-spot refers to a local outbreak of persistent poverty typologies. Circle-based spatial-scan statistics is a popular approach, now widely used by many governments and academic research teams. In this paper we define a [0;1] valued fuzzy poverty measure for the census sections in the urban area of Bari, Apulia, Italy. The scan statistics (SaTScan) and other methods (DBSCAN) were used to successfully identifying poverty clusters. The implications for digital governance are also discussed.
Statistical Methods for Detecting Geographical Clustering of Housing Poverty / MONTRONE S; PERCHINUNNO P; MASSARI A; LIGORIO C; L'ABBATE S. - In: RIVISTA ITALIANA DI ECONOMIA, DEMOGRAFIA E STATISTICA. - ISSN 0035-6832. - LXV n.3/4(2011), pp. 157-164.
Statistical Methods for Detecting Geographical Clustering of Housing Poverty
MONTRONE, Silvestro;PERCHINUNNO, Paola;MASSARI, Antonella;
2011
Abstract
The fuzzy set approach to multidimensional poverty measurement is enjoying increasing popularity. A different, yet strongly related issue concerns geo-informatics surveillance for poverty hot-spot detection: hot-spot refers to a local outbreak of persistent poverty typologies. Circle-based spatial-scan statistics is a popular approach, now widely used by many governments and academic research teams. In this paper we define a [0;1] valued fuzzy poverty measure for the census sections in the urban area of Bari, Apulia, Italy. The scan statistics (SaTScan) and other methods (DBSCAN) were used to successfully identifying poverty clusters. The implications for digital governance are also discussed.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
