haku: @indexterm STATISTICS / yhteensä: 416
viite: 14 / 416
| Tekijä: | Hwang, S. Pereira, P.L.V. |
| Otsikko: | Small sample properties of GARCH estimates and persistence |
| Lehti: | European Journal of Finance
2006 : SEP/OCT, VOL. 12:6-7, p. 473-494 |
| Asiasana: | markets volatility risk estimation statistics sampling models |
| Kieli: | eng |
| Tiivistelmä: | In this study, the ML estimates of the popular GARCH(1,1) model are shown to be significantly negatively biased in small samples. In many cases converged estimates are not possible with Bollerslev's non-negativity conditions. In addition, results also indicate that a high level of persistence in GARCH(1,1) models obtained using a large number of observations has autocorrelations lower than these ML estimates suggest in small samples. It is proposed that at least 250 observations are needed for ARCH(1) models and 500 observations for GARCH(1,1) models. A simple measure of how much GARCH conditional volatility explains squared returns is proposed. |
SCIMA