Clustering Analysis of Spain at the Regional Level for the Life Insurance Sector

A clustering analysis of Spain, at the regional level, addressed to the life insurance sector, is displayed in this paper. Such analysis is based on a set of datasets which was carefully selected and automatedly obtained from Spanish official data. Four models intend to grasp some changes and virtues from a model whose working dataset contains either just mortality rates (model I), or just morbidity rates (model II), or both (model III), to finish with a model with the whole selection of socio-economic and health-related data. Main findings of clustering Spain by regions carried out in this set of analyses are the following ones: (i) clustering based just on mortality and/or morbidity rates can shed some light, but both the interpretations and the clustering divisions obtained are limited; (ii) clustering based on the full selection of socio-economic and health-related data offers a sensible and clearly divided clustering. (iii) The interpretation of the clustering with the full selection of data allows us to discuss and rank regions according to two dimensions: ‘Lifestyle, Health, and Environment’, and ‘Economic stress, unemployment, and mortality and morbidity’. These rankings provide interesting insights concerning the north–south differences in Spain, together with the ones between main cities vs more rural areas.