Combined functionals as risk measures.pptVIP

A. Novosyolov Combined functionals Combined functionals as risk measures Arcady Novosyolov Institute of computational modeling SB RAS, Krasnoyarsk, Russia, 660036 anov@icm.krasn.ru /novosyolov/ Structure of the presentation Risk Example: Finite sample space Risk treatment Risk measure Using risk measures Certain equivalent of a risk Price of a financial asset, portfolio Insurance premium for a risk Goal function in decision-making problems RM: Expectation RM: Expected utility EU as a dollar transform EU is linear in probability EU: Rabins paradox RM: Distorted probability DP as a probability transform DP is positively homogeneous RM: Combined functional CF, risk aversion CF, example parameters CF: Rabins paradox resolved Relations among risk measures Legend for relations Illustrations EU: indifference curves DP: indifference curves CF: indifference curves A few anticipated questions Why are risks assumed bounded? Is EU a certain equivalent? * * Risk Risk measure Relations among risk measures RM: Expectation RM: Expected utility RM: Distorted probability RM: Combined functional Anticipated questions Illustrations Risk is an almost surely bounded random variable Another interpretation: risk is a real distribution function with bounded support Correspondence: Why bounded? Back to structure Next Previous Let the sample space be finite: Then: Probability distribution is a vector Random variable is a vector Distribution function is a step function Back to structure 1 Next Previous Here risk is treated as gain (the more, the better). Examples: ? Return on a financial asset 0.9 0.1 p 20% 0% x 0.98 0.02 p $0 -$1,000,000 x ? Insurable risk ? Profit/loss distribution (in thousand dollars) 0.21 0.65 0.13 0.01 p 30 10 -5 -20 x Back to structure Next Previous Risk measure is a real-valued functional or Risk measures allowing both representations with Back to structure are called law invariant. Next Previous Back to structure Next Previous Expectation is a very simple law invaria