Return Predictability Revisited Using Weighted Least Squares
Year: 2017
Type: preprint
Abstract: Time varying volatility causes substantial heteroskedasticity in return predictability regressions, making OLS estimates less efficient than least squares estimates weighted by ex-ante return variance (WLS-EV). In small sample simulations, I show that using WLS-EV instead of OLS results in large efficiency gains, fewer false negatives, and avoids the bias associated with ex-post weighting schemes. Using WLS-EV also changes several important conclusions based on OLS estimates: traditional predictors such as the dividend-to-price ratio perform better in- and out-of-sample, whereas WLS-EV estimates of the predictability afforded by proxies for the variance risk premium, politics, the weather, and the stars are not significant.
Source: SSRN Electronic Journal
Author: Travis L. Johnson
Language: English
Subfield: Finance
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W32810983