A new index for measuring the dependence between two risks

This talk proposes a new index to measure the degree of dependence between two risks, which assumes a value between zero and one and is equal to zero if and only if the risk is subindependent. The concept of subindependence is stronger than uncorrelatedness but weaker than independence. The proposed index is based on the characteristic function and can be simplified into the expression of moments. We study its theoretical properties and show that there is a very simple calculation formula for the corresponding statistical measure. Their asymptotic properties and applications are also discussed.

尹传存，曲阜师范大学二级教授。 已主持多项国家自然科学基金和省部级项目。近期研究兴趣为风险度量、随机序、多元统计分析等。已在国内外学术刊物上发表SCI及SSCI论文100余篇, 其中包括《Bernoulli》 《IME》《ASTIN Bull》《SAJ》《EJOR》《JMVA》等刊物。 现担任期刊Communications in Statistics-Theory and Methods 等3个系列刊物的副主编（AE），期刊Mathematical Methods of Statistics 编委。