STRESS TESTING FOR RISK-AVERSE STOCHASTIC PROGRAMS

Abstract

Possible use of the contamination technique in stress testing of risk measures and risk-averse stochastic programs was initiated by Dupačová and Polívka and detailed for the Value at Risk (VaR) and the Conditional Value at Risk (CVaR). In this paper we discuss several extensions of the approach, namely to stress testing for multistage risk-averse stochastic programs with CVaR related objectives, and for spectral and polyhedral risk measures.

Keywords

• Stochastic programing
• robustness
• stress testing
• contamination
• CVaR
• spectral risk measures