On the Economic Significance of Stock Return Predictability

Kandel and Stambaugh (1996) demonstrate that forecasting variables with weak statistical support in predictive return regressions can exert considerable economic influence on portfolio decisions. Using a Bayesian vector autoregression framework with stochastic volatility in market returns and predictor variables, we assess the economic value of return predictability for investors and reach a complementary conclusion. Statistically strong predictors can be economically unimportant if they tend to take extreme values in high-volatility periods, have low persistence, or follow distributions with fat tails. Several popular predictors exhibit these properties such that their impressive statistical results do not translate into large economic gains.