Metodi di Forward Search per la ricerca di outlier: un’applicazione ai dati Istat sui matrimoni nel 2011

Simona Toti (toti@istat.it), Romina Filippini (filippini@istat.it), Francesco Amato (framato@istat.it) and Claudia Iaccarino (iaccarin@istat.it)
Additional contact information
Simona Toti: Italian National Institute of Statistics
Romina Filippini: Italian National Institute of Statistics
Francesco Amato: Italian National Institute of Statistics
Claudia Iaccarino: Italian National Institute of Statistics

Rivista di statistica ufficiale, 2014, vol. 16, issue 1-2, 31-44

Abstract: Forward Search (FS) is an iterative method to detect the presence of groups of outliers in the case of regression or multivariate data. In the present paper, FS is applied to Istat data on marriages celebrated in 2011 and to the characteristics of partners. The aim is to identify Provinces and Municipalities with significantly different characteristics from the other Italian Provinces and Municipalities. The analysis was conducted referring to three FS models: the multivariate, the compositional and the regression model. The comparison of the results obtained highlights the importance of the reference framework to define an observation as outlier. The analysis was performed using SiRiO (Outlier Research System), a software developed in Istat to make the FS analysis available for non- expert users.

Keywords: Outlier; Forward Search; . (search for similar items in EconPapers)
JEL-codes: C80 C83 C88 (search for similar items in EconPapers)
Date: 2014
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.istat.it/it/files/2014/10/Articolo-3_Metodi-fi-Forward....pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:isa:journl:v:16:y:2014:i:1-2:p:31-44

Access Statistics for this article

More articles in Rivista di statistica ufficiale from ISTAT - Italian National Institute of Statistics - (Rome, ITALY) Contact information at EDIRC.
Bibliographic data for series maintained by Stefania Rossetti (strosset@istat.it).