期刊名称:Documents de Travail du Centre d'Economie de la Sorbonne
印刷版ISSN:1955-611X
出版年度:2017
出版社:Centre d'Economie de la Sorbonne
摘要:Unimodal probability distribution has been widely used for Value-at-Risk(VaR) computation by investors, risk managers and regulators. However, nan-cial data may be characterized by distributions having more than one modes.Using a unimodal distribution may lead to bias for risk measure computation.In this paper, we discuss the inuence of using multimodal distributions on VaRand Expected Shortfall (ES) calculation. Two multimodal distribution familiesare considered Cobb's family and distortion family. We provide two ways tocompute the VaR and the ES for them an adapted rejection sampling techniquefor Cobb's family and an inversion approach for distortion family. For empiricalstudy, two data sets are considered a daily data set concerning operational riskand a three month scenario of market portfolio return built with ve minutesintraday data. With a complete spectrum of condence levels from 0001 to0999, we analyze the VaR and the ES to see the interest of using multimodaldistribution instead of unimodal distribution.