股指期货波动率的半参数预测模型及其MCS检验

发布时间：2018-05-30 22:09

本文选题：半参数预测模型 + 股指期货　；参考：《中山大学学报(自然科学版)》2013年04期

【摘要】：股指期货在资本市场价格发现和风险防范过程中扮演重要角色,科学准确的预测其收益波动率对充分实现股指期货的市场功能具有重要的理论和现实价值。将线性非负模型扩展为半参数的预测模型,用来预测股指期货市场的已实现波动率,并探讨了该模型估计方法的渐进性质。此外,以沪深300股指期货的5 min高频交易数据为例,运用滚动时间窗的样本外预测和最新发展起来的具有Bootstrap特性的MCS检验,在多种稳健损失函数下,实证评价和比较新构建的半参数预测模型与其他7类波动率预测模型对沪深300股指期货已实现波动率的预测能力。实证结果表明,在多种稳健损失函数的评价标准下,新构建的半参数预测模型是预测性能最好的模型。
[Abstract]:Stock index futures play an important role in the process of price discovery and risk prevention in the capital market. It is of great theoretical and practical value to predict the volatility rate of stock index futures in a scientific and accurate way to fully realize the market function of stock index futures. The linear nonnegative model is extended to a semi-parametric prediction model to predict the realized volatility in the stock index futures market. The asymptotic properties of the model estimation method are discussed. In addition, taking the 5 min high-frequency trading data of Shanghai and Shenzhen 300 stock index futures as an example, using the extrasample prediction of rolling time window and the newly developed MCS test with Bootstrap characteristics, under a variety of robust loss functions, Empirical evaluation and comparison of the newly constructed semi-parametric forecasting model and other seven kinds of volatility forecasting model for the Shanghai and Shenzhen 300 stock index futures have realized volatility prediction ability. The empirical results show that the new semi-parametric prediction model is the best one under the evaluation criteria of various robust loss functions.
【作者单位】：华南农业大学经济管理学院;中山大学国际商学院;
【基金】：国家自然科学基金资助项目(71203067) 广东省高校优秀青年创新人才培育计划资助项目(育苗项目)(2012WYM_0033,wym_11004) 广东省哲学社会科学规划资助项目(GD11YLJ01) 中央高校基本科研业务费专项资金中山大学青年教师培育资助项目(13wkpy21) 广东省高等学校高层次人才资助项目中山大学985工程三期建设资助项目
【分类号】：F224;F832.5

【参考文献】