Safety-first analysis and stable Paretian approach to portfolio choice theory

In this paper, we present some characterizations of efficient sets using the stochastic dominance rules and comparing the safety-first approach with the stable Paretian analysis. We introduce a new stable Paretian version of the Markowitz financial optimization model in order to find an optimal frontier based on a more realistic model for the distribution of asset returns. As a generalization of moments analysis, we consider a portfolio selection for an investor who wishes to allocate his initial wealth across n investments with returns following general heavy-tailed distributions. Alternatively, we show that the safety-first approach can be more efficient than the stable Paretian approach. Finally, we present two possible direct methods for portfolio choice in a safety-first world.