Working Paper: NBER ID: w11903
Authors: Andrew Ang; Joseph Chen
Abstract: A conditional one-factor model can account for the spread in the average returns of portfolios sorted by book-to-market ratios over the long run from 1926-2001. In contrast, earlier studies document strong evidence of a book-to-market effect using OLS regressions in the post-1963 sample. However, the betas of portfolios sorted by book-to-market ratios vary over time and in the presence of time-varying factor loadings, OLS inference produces inconsistent estimates of conditional alphas and betas. We show that under a conditional CAPM with time-varying betas, predictable market risk premia, and stochastic systematic volatility, there is little evidence that the conditional alpha for a book-to-market trading strategy is statistically different from zero.
Keywords: CAPM; Book-to-Market; Time-Varying Betas; Conditional Alpha
JEL Codes: C51; G12
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| traditional OLS regression (C29) | inconsistent estimates of conditional alphas and betas (C51) |
| time-varying betas (C22) | evidence for a book-to-market effect is weaker than previously believed (G14) |
| rolling OLS estimates of betas (C51) | understates the variance of true conditional betas (C46) |
| conditional CAPM with time-varying betas (C22) | average returns of portfolios sorted by book-to-market ratios (G11) |
| conditional CAPM with time-varying betas (C22) | conditional alpha for a book-to-market trading strategy is statistically different from zero (C46) |