This article considers whether the widely documented momentum profits are a compensation for time-varying unsystematic risk as described by the family of autoregressive conditionally heteroscedastic models. The motivation for estimating a GJR-GARCH(1,1)-M model stems from the fact that, since losers have a higher probability than winners to disclose bad news, one cannot assume a symmetric response of volatility to good and bad news. A revisited version of this paper was published in the April 2008 issue of the Journal of Banking & Finance.
This article considers whether the widely documented momentum profits are a compensation for time-varying unsystematic risk as described by the family of autoregressive conditionally heteroscedastic models. The motivation for estimating a GJR-GARCH(1,1)-M model stems from the fact that, since losers have a higher probability than winners to disclose bad news, one cannot assume a symmetric response of volatility to good and bad news. A revisited version of this paper was published in the April 2008 issue of the Journal of Banking & Finance.
Type : | Working paper |
---|---|
Date : | 30/09/2006 |
Keywords : |
Performance Measurement |