This paper shows how it is possible to estimate the interconnections between regions by a connectedness matrix recently proposed by Diebold and Yilmaz (2014), and discusses how the connectedness matrix is strictly related to the spatial weights matrix used in spatial econometrics. An empirical application using growth rate volatility of per capita GDP of 199 European NUTS2 regions (EU15) over the period 1981-2008 illustrates how our estimated connectedness matrix is not compatible with the most popular geographical weights matrices used in literature.
How Reliable Are the Geographical Spatial Weights Matrices?
FIASCHI, DAVIDE;PARENTI, ANGELA
2014-01-01
Abstract
This paper shows how it is possible to estimate the interconnections between regions by a connectedness matrix recently proposed by Diebold and Yilmaz (2014), and discusses how the connectedness matrix is strictly related to the spatial weights matrix used in spatial econometrics. An empirical application using growth rate volatility of per capita GDP of 199 European NUTS2 regions (EU15) over the period 1981-2008 illustrates how our estimated connectedness matrix is not compatible with the most popular geographical weights matrices used in literature.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
4_Fiaschi_Parenti2(2).pdf
accesso aperto
Tipologia:
Versione finale editoriale
Licenza:
Creative commons
Dimensione
1.02 MB
Formato
Adobe PDF
|
1.02 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.