Working Paper: NBER ID: w12026
Authors: John H. Cochrane
Abstract: To question the statistical significance of return predictability, we cannot specify a null that simply turns off that predictability, leaving dividend growth predictability at its essentially zero sample value. If neither returns nor dividend growth are predictable, then the dividend-price ratio is a constant. If the null turns off return predictability, it must turn on the predictability of dividend growth, and then confront the evidence against such predictability in the data. I find that the absence of dividend growth predictability gives much stronger statistical evidence against the null, with roughly 1-2% probability values, than does the presence of return predictability, which only gives about 20% probability values. I argue that tests based on long-run return and dividend growth regressions provide the cleanest and most interpretable evidence on return predictability, again delivering about 1-2% probability values against the hypothesis that returns are unpredictable. I show that Goyal and Welch's (2005) finding of poor out-of-sample R2 does not reject return forecastability. Out-of-sample R2 is poor even if all dividend yield variation comes from time-varying expected returns.
Keywords: Return Predictability; Dividend Growth; Financial Markets
JEL Codes: G0; G1
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| lack of dividend growth predictability (G35) | return predictability (C53) |
| dividend yields (G35) | expected returns (G17) |
| dividend-price ratio (G35) | stock returns (G12) |
| dividend yields (G35) | future dividend growth (G35) |
| dividend-price ratio (G35) | dividend growth (G35) |