Portfolio selection in the BRICs stocks markets using Markov processes

In this paper, we examine the performance of classical portfolio strategies in the BRIC's stock markets using a Markov approximation of the portfolio returns. In particular, we try to evaluate whether these markets can be a valid investment for non satiable and risk averse investors. First, we examine the main statistical characteristics of the returns in each market. Secondly, we provide a methodology to approximate the portfolios sample paths when the returns follow a Markov process. Finally, we examine the profitability of the classic investment strategies in each of the four BRICs markets individually and in all markets jointly, under the assumption the returns are approximated by a non parametric Markov chain. In particular, we compare the ex-post sample paths of the wealth obtained optimizing a mean - variance performance with and without assuming the Markovian hypothesis.