Intrinsic bubbles revisited : evidence from nonlinear cointegration and forecasting
Journal of Forecasting
Forecasting, Intrinsic bubbles, Kalman filter, Nonlinear cointegration, Random walk
This paper offers strong further empirical evidence to support the intrinsic bubble model of stock prices, developed by Froot and Obstfeld (American Economic Review, 1991), in two ways. First, our results suggest that there is a long-run nonlinear relationship between stock prices and dividends for the US stock market during the period 1871-1996. Second, we find that the out-of-sample forecasting performance of the intrinsic bubbles model is significantly better than the performance of two alternatives, namely the random walk and the rational bubbles model.
Copyright © 2004 John Wiley & Sons, Ltd. Access to external full text or publisher's version may require subscription.
Ma, Y., & Kanas, A. (2004). Intrinsic bubbles revisited: Evidence from nonlinear cointegration and forecasting. Journal of Forecasting, 23(4), 237-250. doi: 10.1002/for.909