Ricerc@Sapienza

This study aims to assess whether simple, widely available demographic indexes, like mortality measures, may serve as sentinel indicators of the economic development and the social wellbeing in Italy. We analyze and compare the geographical patterns of all-cause mortality indexes and those of the mortality rates for leading causes of death, with the spatial pattern found for a more complex index, the vulnerability index, recently introduced by the Italian National Institute for Statistics, at provincial level in the contemporary Italy.

Multivariate spatial count data are often segmented by unobserved space-varying factors that vary across space. In this setting, regression models that assume space-constant covariate effects could be too restrictive. Motivated by the analysis of cause-specific mortality data, we propose to estimate space-varying effects by exploiting a multivariate hidden Markov field. It models the data by a battery of Poisson regressions with spatially correlated regression coefficients, which are driven by an unobserved spatial multinomial process.