UNCOVERING NONLINEAR STRUCTURE IN REAL-TIME STOCK-MARKET INDEXES - THE S-AND-P-500, THE DAX, THE NIKKEI-225, AND THE FTSE-100

This article tests for nonlinear dependence and chaos in real-time ret urns on the world's four most important stock-market indexes. Both the Brock-Dechert-Scheinkman and the Lee, White, and Granger neural-netwo rk-based tests indicate persistent nonlinear structure in the series. Estimates of the Lyapunov exponents using the Nychka, Ellner, Gallant, and McCaffrey neural-net method and the Zeng, Pielke, and Eyckholt ne arest-neighbor algorithm confirm the presence of nonlinear dependence in the returns on all indexes but provide no evidence of low-dimension al chaotic processes. Given the sensitivity of the results to the esti mation parameters, we conclude that the data are dominated by a stocha stic component.