Although the unstoppable evolution of Information Technology allows nowadays for the treatment of massive socio-economic data, reliable historical data for forecasting are not always widely available for applying statistical models from which significant parameters can be obtained. This becomes a paradox in regional forecasting where data can be widely available but often can be useless. The aim of this work is to present a method for improving forecasting precision with few information. After a brief description of the most popular techniques in this field, an application on regional forecasting with hierarchical conciliation is presented.
"Infinite" data and few information for regional forecast: an applied approach from this paradox / P.M. Chiodini, S. Facchinetti, G. Manzi, F. Verrecchia - In: Proceedinggs of the Italian Statistical Society Scientific Meeting - 2009[s.l] : Italian Statistical Society, 2009. - ISBN 9788861294257. (( convegno Italian Statistical Society Intermediate Meeting - 2009 tenutosi a Pescara, Italy nel 2009.
"Infinite" data and few information for regional forecast: an applied approach from this paradox
G. ManziPenultimo
;
2009
Abstract
Although the unstoppable evolution of Information Technology allows nowadays for the treatment of massive socio-economic data, reliable historical data for forecasting are not always widely available for applying statistical models from which significant parameters can be obtained. This becomes a paradox in regional forecasting where data can be widely available but often can be useless. The aim of this work is to present a method for improving forecasting precision with few information. After a brief description of the most popular techniques in this field, an application on regional forecasting with hierarchical conciliation is presented.File | Dimensione | Formato | |
---|---|---|---|
SIS2009_ext_paper_CFMV.pdf
accesso aperto
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
147.81 kB
Formato
Adobe PDF
|
147.81 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.