Discussion Papers in Statistics and Econometrics No. 9/07
University of Cologne, Seminar of Economic and Social Statistics, Cologne
Pearson's correlation coefficient is typically used for measuring the dependence structure of stock returns. Nevertheless, it has many shortcomings often documented in the literature. We suggest to use a conditional version of Spearman's rho as an alternative dependence measure. Our approach is purely nonparametric and we avoid any kind of model misspecification. We derive hypothesis tests for the conditional Spearman's rho in bull andbearmarkets and verify the tests by Monte Carlo simulation.Further, we study the daily returns of stocks contained in the German stock index DAX 30. We find some significant differences in dependence of stock returns in bull and bear markets. On the other hand the differences are not so strong as one might expect.
bear market bootstrapping bull market conditional Spearman's rho copulas Monte Carlo simulation stock returns