An evolving possibilistic fuzzy modeling approach for value-at-risk estimation

Market risk exposure plays a key role for nancial institutions risk management. A possible measure for this exposure is to evaluate losses likely to incurwhen the price of the portfolio's assets declines using Value-at-Risk (VaR) estimates, one of the most prominent measure of nancial downside market risk. This paper suggests an evolving possibilistic fuzzy modeling approach for VaR estimation. The approach is based on an extension of the possibilistic fuzzy c-means clustering and functional fuzzy rule-based modeling, which employs memberships and typicalities to update clusters and creates new clusters based on a statistical control distance-based criteria. ePFM also uses an utility measure to evaluate the quality of the current cluster structure. Computational experiments consider data of the main global equity market indexes of United States, London, Germany, Spain and Brazil from January 2000 to December 2012 for VaR estimation using ePFM, traditional VaR benchmarks such as Historical Simulation, GARCH, EWMA, and Extreme Value Theory and state of the art evolving approaches. The results show that ePFM is a potential candidate for VaR modeling, with better performance than alternative approaches.

Spatial spillovers and political coordination in public health provision

We estimate the impact of the main unconditional federal grant (Fundo de Participaçãodos Municípios - FPM) to Brazilian municipalities as well as its spillover from the neighboring cities on local health outcomes. We consider data from 2002 to 2007 (Brollo et al, 2013) and explore the FPM distribution rule according to population brackets to apply a fuzzy Regression Discontinuity Design (RDD) using cities near the thresholds. In elasticity terms, we nd a reduction on infant mortality rate (-0.18) and on morbidity rate (- 0.41), except in the largest cities of our sample. We also nd an increase on the access to the main program of visiting the vulnerable families, the Family Health Program (Programa Sa ude da Família - PSF). The e ects are stronger for the smallest cities of our sample and we nd increase: (i) On the percentage of residents enrolled in the program (0.36), (ii) On the per capita number of PSF visits (1.59), and (iii) On the per capita number of PSF visits with a doctor (1.8) and nurse (2). After we control for the FPM spillover using neighboring cities near diferent thresholds, our results show that the reduction in morbidity and mortality is largely due to the spillover e ect, but there are negative spillover on preventive actions, as PSF doctors visits and vaccination. Finally, the negative spillover e ect on health resources may be due free riding or political coordination problems, as in the case of the number of hospital beds, but also due to to competition for health professionals, as in the case of number of doctors (-0.35 and -0.87, respectively), specially general practitioners and surgeons (-1.84 and -2.45).