Working Paper: NBER ID: w17334
Authors: Jessica A. Wachter; Missaka Warusawitharana
Abstract: We examine the evidence on excess stock return predictability in a Bayesian setting in which the investor faces uncertainty about both the existence and strength of predictability. When we apply our methods to the dividend-price ratio, we find that even investors who are quite skeptical about the existence of predictability sharply modify their views in favor of predictability when confronted by the historical time series of returns and predictor variables. Correctly taking into account the stochastic properties of the regressor has a dramatic impact on inference, particularly over the 2000-2005 period.
Keywords: equity premium; stock return predictability; Bayesian analysis; dividend-price ratio
JEL Codes: C11; C22; G11; G17
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| dividend-price ratio (G35) | excess stock returns (G12) |
| historical data (Y10) | belief in predictability (D84) |
| initial observation of predictor variable (C29) | estimation of unconditional risk premium (C13) |
| 2000-2005 period (F29) | belief in predictability (D84) |
| fixed regressors (C29) | belief in predictability (D84) |