- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
We present a simple methodology for modeling the time variation in volatilities and other higher-order moments using a recursive updating scheme that is similar to the familiar RiskMetricsTM approach. The parameters are updated using the score of the forecasting distribution, which allows the parameter dynamics to adapt automatically to any nonnormal data features, and increases the robustness of the subsequent estimates. The new approach nests several of the earlier extensions to the exponentially weighted moving average (EWMA) scheme. In addition, it can be extended easily to higher dimensions and alternative forecasting distributions. The method is applied to Value-at-Risk forecasting with (skewed) Student’s t distributions and a time-varying degrees of freedom and/or skewness parameter. We show that the new method is as good as or better than earlier methods for forecasting the volatility of individual stock returns and exchange rate returns. © 2015 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.
We have developed a range of simple EWMA refinements that build on the recent literature on score-driven dynamics for time-varying parameters in non-normal models. In this paper we have shown that the standard EWMA and the robust Laplace based EWMA can be seen as special cases of the new score-driven EWMA (SDEWMA) approach. In particular, as financial return series may typically be fat-tailed rather than heavy-tailed (such as Laplace), we developed a score-driven EWMA scheme based on the symmetric and skewed Student’s t distributions. As the score-driven approach is not limited to time variation in volatilities only, we also developed a new SDEWMA scheme for the simultaneous time series dynamics of the volatility, the degrees of freedom, and possibly the skewness parameter in a (skewed) Student’s t distribution. The new schemes exhibit interesting robustness features for the time-varying parameter dynamics that make themparticularly suitable in a context with non-Gaussian distributed observations.