Working Paper: NBER ID: w17561
Authors: Andrew Ang; Dennis Kristensen
Abstract: Using nonparametric techniques, we develop a methodology for estimating conditional alphas and betas and long-run alphas and betas, which are the averages of conditional alphas and betas, respectively, across time. The tests can be performed for a single asset or jointly across portfolios. The traditional Gibbons, Ross, and Shanken (1989) test arises as a special case of no time variation in the alphas and factor loadings and homoskedasticity. As applications of the methodology, we estimate conditional CAPM and multifactor models on book-to-market and momentum decile portfolios. We reject the null that long-run alphas are equal to zero even though there is substantial variation in the conditional factor loadings of these portfolios.
Keywords: Conditional Models; Asset Pricing; Factor Models; Nonparametric Estimation
JEL Codes: C12; C13; C14; C32; G12
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| time-varying factor loadings (C22) | rejection of null hypothesis of long-run alphas being equal to zero (C12) |
| ignoring time-varying betas (C22) | misleading conclusions about asset pricing (G19) |
| long-run alphas of book-to-market portfolios (G11) | rejection of conditional CAPM (G19) |
| long-run alphas (C51) | convergence at standard parametric rates (F62) |
| conditional alpha estimators (C51) | inconsistent without additional restrictions (C62) |