Coherent measures of Risk一致风险测度.ppt

Geometrical interpretation If any point represents a given coherent measure ... ... Then any other point in the generated “convex hull” is a new coherent measure of risk Given n coherent measures, their most general convex combination is any of the points contained in the generated “convex hull” Our strategy .... Set of all Expected Shortfalls with ??(0,1] Convex hull = New space of coherent measures We already know infinitely many coherent measures of risk, namely all the possible ?-Expected Shortfalls for any value ? between 0 e 1 In this way we can generate a new class of coherent measures. This class is defined “Spectral Measures of Risk” Spectral measures of risk: explicit characterization Definition: Spectral measure of risk with spectrum Theorem: the measure M?(X) is coherent if and only if is positive is not increasing The “Risk Aversion Function” ?(p) Any admissible ?(p) represents a possible legitimate rational attitude toward risk A rational investor may express her own subjective risk aversion through her own subjective ?(p) which in turns give her own spectral measure M? ?(p): Risk Aversion Function Best cases Worst cases It may thought of as a function which “weights” all cases from the worst to the best “?(p) decreasing” explains the essence of coherence ...a measure is coherent only if it maps “bigger weights to worse cases” Risk Aversion Function ?(p) for ES and VaR Expected Shortfall: Step function positive decreasing Value at Risk: Spike function (Dirac delta) positive not decreasing Estimating Spectral Measures of Risk It can be shown that any spectral measure has the following consistent estimator: Discretized ? function Ordered statistics (= data sorted from worst to best) Tailoring Risks ! The Expected Shortfall is just one out of infinitely many possible Spectral Measures ES expresses just a specific risk aversion But is there a spectral measure which is optimal for all portfolio