CAJ | 학술논문

利用上海期货交易所线材期货15分钟高频价格数据构造已实现波动率估计序列,并以此作为参考标准,运用6种损失函数以及Diebold-Mariano检验法检验4类不同波动率模型对线材期货价格波动的样本外预测能力,显示,中国线材期货市场,基于高频数据的GJR（1,1）模型具有最为出色的波动率预测能力,而在某些损失函数标准下,HYGARCH（1,d,1）与GARCH（1,1）模型也体现出了较好的波动率预测能力。
이용상해기화교역소선재기화15분종고빈개격수거구조이실현파동솔고계서렬,병이차작위삼고표준,운용6충손실함수이급Diebold-Mariano검험법검험4류불동파동솔모형대선재기화개격파동적양본외예측능력,현시,중국선재기화시장,기우고빈수거적GJR（1,1）모형구유최위출색적파동솔예측능력,이재모사손실함수표준하,HYGARCH（1,d,1）여GARCH（1,1）모형야체현출료교호적파동솔예측능력。
Taking the 15 minutes of high-frequency price data of wire rod futures in Shanghai Futures Exchange as an example, this paper builds realized volatility estimator sequence, and uses it as reference standard to employ six kinds of loss Rmctions as well as Diebold ＇-of Mariano test method to empirically examine the predictive capabilities of four models with different volatility on a sample of wire rod futures price volatility. The empirical results show that China＇s wire rod futures market based on high frequency data of GJR（1,1） model has the most excellent volatility predictive ability,and under the standard of some function loss, HYGARCH （1 ,d, 1） and GARCH（1,1） model also reflect good predictive ability of volatility.