DYNAMIC STYLE ANALYSIS OF BRAZILIAN HEDGE FUNDS

Abstract

This paper applies the traditional return-based style analysis (RBSA) in the presence of time-varying exposures. Often the investment style is assumed to be constant through time. Alternatively, time variation is sometimes implicitly accounted for by using rolling regressions when estimating the style analysis. We use the Kalman filter to model time-varying exposures of hedge funds explicitly. This leads to a testable model and more efficient use of the data, which reduces the influence of spurious correlation between hedge fund returns and style indices. The aim of this study is to estimate the investment styles and reveal periodic return distributions of Brazilian hedge funds for the 2006-2011 period. In a large sample of funds, we find substantial evidence that hedge fund risk exposures vary along the time. We also find that the exposition to fixed income is increasing over the last years. The results have shown that style analyses explain over 50% of the funds returns. Finally, we analyze exposures during the global financial crisis (2008-2009).