This paper will discuss a recently proposed index for measuring seasonality, which is based on the solution of the well-known transportation problem . A specific characterization of the cost matrix will permit the taking into account of the cyclical structure of time periods, which characterizes the phenomenon under observation. Various features of the proposed index will be evaluated by comparing it with other indices which are commonly used in the measurement of seasonality, such as the Gini concentration index. Given the wide range of disciplines with an interest in the analysis of seasonal phenom ena, the approach proposed m ay be of wide interest.
Giovanni L. Lo Magno, M.F. (2017). A comparison between seasonality indices deployed in evaluating unimodal and bimodal patterns. In Proceedings of the Conference of the Italian Statistical Society - SIS 2017 Statistics and Data Science: new challenges, new generations (pp.607-612). Firenze : Firenze University Press, 2017.
A comparison between seasonality indices deployed in evaluating unimodal and bimodal patterns
Giovanni L. Lo Magno;Mauro Ferrante;Stefano De Cantis
2017-01-01
Abstract
This paper will discuss a recently proposed index for measuring seasonality, which is based on the solution of the well-known transportation problem . A specific characterization of the cost matrix will permit the taking into account of the cyclical structure of time periods, which characterizes the phenomenon under observation. Various features of the proposed index will be evaluated by comparing it with other indices which are commonly used in the measurement of seasonality, such as the Gini concentration index. Given the wide range of disciplines with an interest in the analysis of seasonal phenom ena, the approach proposed m ay be of wide interest.File | Dimensione | Formato | |
---|---|---|---|
Sis_new_index.pdf
Solo gestori archvio
Descrizione: Articolo principale
Dimensione
542.23 kB
Formato
Adobe PDF
|
542.23 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.