he paper presents the analysis of unemployment duration data gathered by ISTAT in Emilia Romagna, from 1st quarter 1993 to 1st quarter 1995. Exploiting the 2-2-2 rotating scheme of the survey, a set of completed spells was obtained from the nine originally available samples of incomplete ones. Both data sets were modelled by the Weibull distribution. Therefore, referring to the incomplete spells, it was assumed that the unobserved completed spells were Weibull distributed. The empirical distributions of spell durations showed pronounced spikes, which suggest the presence of a considerable telescopic effect. This effect was modelled by an exponential heaping function. Heterogeneity was controlled for by adding a suitable set of covariates. The full model was estimated separately on the completed spells data and for each quarter of the incomplete spells data, to control for potential seasonal effect.
Analisi della durata della disoccupazione su dati longitudinali e trasversali: il caso Emilia-Romagna / Lalla, Michele; Pattarin, Francesco. - STAMPA. - II:(1999), pp. 551-558. (Intervento presentato al convegno XXXIX Riunione Scientifica della SIS tenutosi a Sorrento nel 14-17 aprile 1998).
Analisi della durata della disoccupazione su dati longitudinali e trasversali: il caso Emilia-Romagna
LALLA, Michele;PATTARIN, Francesco
1999
Abstract
he paper presents the analysis of unemployment duration data gathered by ISTAT in Emilia Romagna, from 1st quarter 1993 to 1st quarter 1995. Exploiting the 2-2-2 rotating scheme of the survey, a set of completed spells was obtained from the nine originally available samples of incomplete ones. Both data sets were modelled by the Weibull distribution. Therefore, referring to the incomplete spells, it was assumed that the unobserved completed spells were Weibull distributed. The empirical distributions of spell durations showed pronounced spikes, which suggest the presence of a considerable telescopic effect. This effect was modelled by an exponential heaping function. Heterogeneity was controlled for by adding a suitable set of covariates. The full model was estimated separately on the completed spells data and for each quarter of the incomplete spells data, to control for potential seasonal effect.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
