Adaptive Macroeconomic Diffusion Indexes: Nexus Connecting Business Cycles to Real-time Equity Premium Prediction

This paper constructs macro indexes as quantitative descriptions of business cycles and explores the linkages between business conditions and the equity premium. I find that adaptively selected macro indexes explain a substantial fraction of the short-term variation in future stock returns. The performance of macro indexes is superior to the historical average and many prominent predictors. The superior predictive power persists over the most recent three decades. In addition, investment strategies exploiting the real-time conditional forecasts earn excess profits over a buy-and-hold strategy in the market index under moderate transaction costs. The decomposition of diffusion indexes show that the collective effect of several categories — interest rates, price indexes, housing, and employment — bestows the predictability of the equity premium. ∗I sincerely appreciate the encouragement and generous help from my thesis committee: George Constantinides, Ruey Tsay, Lars Hansen, Monika Piazzesi and Alan Bester. I am also grateful to the following for helpful comments: James Stock, Mark Watson, John Cochrane, and seminar participants at the University of Chicago GSB, Southern Methodist University. This paper is Chapter Two of my Ph.D thesis, based on a previous paper titled “Macro Fundamentals: The Equity Premium Prediction”. Any errors or omissions are the responsibility of the author. †Bai: Graduate School of Business, University of Chicago, 5807 S. Woodlawn Ave, Chicago, IL 60637; Email: [email protected]; Tel: (773) 972-7087.