Measuring the Speed of Convergence of Stock Prices: A Nonparametric and Nonlinear Approach

This paper evaluates the speed of convergence across national stock markets employing a nonlinear, nonparametric stochastic model of relative stock prices. We use operational algorithms for estimating general measures of persistence of the relative stock price that are based on two statistical notions: the short memory in mean (SMM) and the short memory in distribution (SMD). Using G7 countries¡¯ stock indices, we obtain strong empirical evidence in favor of the contrarian strategy for France, Germany, Italy, and the UK relative to the US market, while our results imply quite limited usefulness of the strategy for Canada and Japan. Further, we obtain fairly fast convergence rates toward the equilibrium for the former group.