Answers are grounded in this paper and cite their sources.
We discuss the coherence properties of Expected Shortfall (ES) as a financial risk measure. This statistic arises in a natural way from the estimation of the "average of the 100p % worst losses" in a sample of returns to a portfolio. Here p is some fixed confidence level. We also compare several alternative representations of ES which turn out to be more appropriate for certain purposes.
No takes yet. Share an insight, caveat, or question.
Acerbi et al. (2001) studied this question.