Threshold Random Walks in the U.S. Stock Market

This paper extends the work in Serletis and Shintani (2003) and Elder and Serletis ( 2006) by re-examining the empirical evidence for random walk type behavior in the U.S. stock market. In doing so, it tests the random walk hypothesis by employing unit-root tests that are designed to have more statistical power against nonlinear al- ternatives. The nonlinear feature of our model is re ected by three regimes, one of which is characterized by a unit root process and the random walk hypothesis while the lower and upper regimes are well captured by a stationary autoregressive process with mean reversion and predictability.