We propose an alternative pairs trading strategy based on computing a mispricing index in a novel way via a mixed copula model, or more specifically via an optimal linear combination of copulas. We evaluate the statistical and economic performances of our proposed approach by analyzing S&P 500 daily stock returns between 1990 and 2015. Empirical results are obtained not only from the full sample analysis but also from subperiods analyses. These subperiods are chosen in two different ways: i) fixed time length; and ii) bull/bear market dependent. The fixed time length analysis is able to capture possible dynamics changes over time whereas the bull/bear analysis makes it possible for one to have distinct pairs trading strategies depending on the market state. Our results suggest that two-component mixed copulas perform very well, especially during bear market times when it regards to mean returns.

Keywords: Pairs Trading, Copula, Distance, Quantitative Strategies, S&P 500, Statistical Arbitrage.

Continue reading here.