数苑经纬讲坛（119）：Realized Copula of Volatility
来源：
发布时间：2026-10-10
报告时间：- 2026年10月17日（周六）上午8:30-9:30
- 报告地点：
- 腾讯会议：315-971-163
- 报告人：
- 刘志
- 报告人单位：
- 澳门大学
- 邀请人：
- 晏挺
- 摘要：
- Asset empirical volatility is random. The statistical inference on the volatility itself, conditional on the volatility path, has been well established. However, the inference on the distribution of the stochastic volatility is yet to be well studied, particularly for the multivariate case. In the work, we study the copula of the distributions of bivariate stochastic volatility. We propose realized copula based on estimators of the spot volatility, and establish both infill and long-span asymptotics. Simulation studies based on two well-known stocahstic volatility models, Heston model and OU process, demonstate good performance of our realized copula in capturing the joint distributional pattern of the bivariate stochastic volatility. We also implement our realized copula to a real high-frequency data including two futures contracts, the E-mini S&P 500 (ES) and the 10-Year Treasury Notes (TY). The results suggest a Gumbel copula with a parameter around 1.6 for two stochastic volatilities. This is a joint work with Kim Christensen, Wenjing Liu and Yoann Potiron.
刘志（澳门大学）
