We propose a generalization of the classical notion of the V @R λ that takes into account not only the probability of the losses, but the balance between such probability and the amount of the loss. This is obtained by defining a new class of law invariant risk measures based on an appropriate family of acceptance sets. The V @R λ and other known law invariant risk measures turn out to be special cases of our proposal. We further prove the dual representation of Risk Measures on P(R).
This paper presents the first methodological proposal of estimation of the ΛVaR. Our approach is dynamic and calibrated to market extreme scenarios, incorporating the need of regulators and financial institutions in more sensitive risk measures. We also propose a simple backtesting methodology by extending the VaR hypothesis-testing framework. Hence, we test our ΛVaR proposals under extreme downward scenarios of the financial crisis and different assumptions on the profit and loss distribution. The findings show that our ΛVaR estimations are able to capture the tail risk and react to market fluctuations significantly faster than the VaR and expected shortfall. The backtesting exercise displays a higher level of accuracy for our ΛVaR estimations.
Recently, financial industry and regulators have enhanced the debate on the good properties of a risk measure. A fundamental issue is the evaluation of the quality of a risk estimation. On the one hand, a backtesting procedure is desirable for assessing the accuracy of such an estimation and this can be naturally achieved by elicitable risk measures. For the same objective, an alternative approach has been introduced by Davis (2016) through the so-called consistency property. On the other hand, a risk estimation should be less sensitive with respect to small changes in the available data set and exhibit qualitative robustness. A new risk measure, the Lambda value at risk (ΛV aR), has been recently proposed by Frittelli et al. (2014), as a generalization of V aR with the ability to discriminate the risk among P&L distributions with different tail behaviour. In this article, we show that ΛV aR also satisfies the properties of robustness, elicitability and consistency under some conditions.
A new risk measure, Lambda value at risk (ΛV aR), has been recently proposed as a generalization of Value at risk (V aR). ΛV aR appears attractive for its potential ability to solve several problems of V aR. This paper provides the first study on the backtesting of ΛV aR. We propose three nonparametric tests which exploit different features. Two tests are based on simple results of probability theory. One test is unilateral and is more suitable for small samples of observations. A second test is bilateral and provides an asymptotic result. A third test is based on simulations and allows for a more accurate comparison among ΛV aRs computed with different assumptions on the asset return distribution. Finally, we perform a backtesting exercise that confirms a higher performance of ΛV aR in respect to V aR especially when it is estimated with distributions that better capture tail behaviour.
We give an axiomatic foundation to Λ-quantiles, a family of generalized quantiles introduced in [7] under the name of Lambda Value at Risk. Under mild assumptions, we show that these functionals are characterized by a property that we call "locality", that means that any change in the distribution of the probability mass that arises entirely above or below the value of the Λ-quantile does not modify its value. We compare with a related axiomatization of the usual quantiles given by C. Chambers in [4], based on the stronger property of "ordinal covariance", that means that quantiles are covariant with respect to increasing transformations. Further, we present a systematic treatment of the properties of Λ-quantiles, refining some of the results of [7] and [3] and showing that in the case of a nonincreasing Λ the properties of Λ-quantiles closely resemble those of the usual quantiles.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.