时 间：2017年9月18日（周一）下午13：00-14：00
地 点：体育外围平台APP紫金港校区行政楼702会议室
主讲人：Dr. Jonathan Yumeng Li， the University of Ottawa
主持人：张惜丽副教授，体育外围平台APP
摘 要：
Most risk measures applied in practice are law-invariant risk measures, which encapsulate risk solely based on the law, equivalently probability distribution, of uncertain outcomes. Many difficulties arise however in characterizing the distribution, which is prone to sampling errors, cognitive biases, and many others. Poor characterizations have led to misleading risk assessments. In this talk, we show how the worst-case risk, i.e. the largest risk level, can be estimated in closed-form for any law invariant risk measure that depends only on the mean and variance of the underlying distribution. Moreover, we provide the exact distributional form of the worst-case distribution, which offers great intuition related to one's choice of a risk spectrum. Our result should well demonstrate why robust risk measures appearing in the recent literature can be practically useful.
主讲人简介：
Jonathan Li is an Assistant Professor in the Telfer School of Management at the University of Ottawa. His research has a particular focus on the use of optimization and statistical methods to deal with risk management problems involving complex forms of uncertainty. Jonathan holds a PhD from the University of Toronto in Operations Research and his work has appeared in FT50 journal such as Management Science.
