Nonlinear Dynamics and Stock Returns

TLDR

Deterministic systems can generate chaotic outputs that resemble stochastic systems, leading to algorithms and statistical tests that detect nonlinear dependence in time series. The authors aim to apply these procedures to stock returns to detect nonlinear dependence. They find evidence of nonlinear dependence in weekly returns of the CRSP value‑weighted index. © 1989 University of Chicago.

Abstract

Simple deterministic systems are capable of generating chaotic output that mimics the output of stochastic systems. For this reason, algorithms have been developed to distinguish between these two alternatives. These algorithms and related statistical tests are also useful in detecting the presence of nonlinear dependence in time series. In this article, the authors apply these procedures to stock returns and find evidence that indicates the presence of nonlinear dependence on weekly returns from the Center for Research in Security Prices value-weighted index. Copyright 1989 by the University of Chicago.