Stéphane Mussard

This article extends the paper of Dagum C. and Costa M. (2004). We further develop the study of multidimensional poverty using fuzzy sets by introducing a mixture of decomposition analysis. The model yields the most relevant dimensions of poverty (health, education, etc.) and the most relevant sub-groups (areas, gender, etc.) in order to identify the main forces that contribute to the overall amount of the state of poverty. These results are useful for decision makers that contemplate socioeconomic policies in favour of poverty reduction. Finally, we apply this decomposition to study the level of poverty of Argentina in 1998.