Modality for scenario analysis and maximum likelihood allocation

DOI10.1016/J.INSMATHECO.2020.12.004zbMATH Open1460.91227arXiv2005.02950OpenAlexW3119186372MaRDI QIDQ2657014FDOQ2657014

Authors: Takaaki Koike, Marius Hofert 

Publication date: 17 March 2021

Published in: Insurance Mathematics \& Economics (Search for Journal in Brave)

Abstract: We study the variability of a risk from the statistical viewpoint of multimodality of the conditional loss distribution given that the aggregate loss equals an exogenously provided capital. This conditional distribution serves as a building block for calculating risk allocations such as the Euler capital allocation of Value-at-Risk. A superlevel set of this conditional distribution can be interpreted as a set of severe and plausible stress scenarios the given capital is supposed to cover. We show that various distributional properties of this conditional distribution, such as modality, dependence and tail behavior, are inherited from those of the underlying joint loss distribution. Among these properties, we find that modality of the conditional distribution is an important feature in risk assessment related to the variety of risky scenarios likely to occur in a stressed situation. Under unimodality, we introduce a novel risk allocation method called maximum likelihood allocation (MLA), defined as the mode of the conditional distribution given the total capital. Under multimodality, a single vector of allocations can be less sound. To overcome this issue, we investigate the so-called multimodalty adjustment to increase the soundness of risk allocations. Properties of the conditional distribution, MLA and multimodality adjustment are demonstrated in numerical experiments. In particular, we observe that negative dependence among losses typically leads to multimodality, and thus a higher multimodality adjustment can be required.

Full work available at URL: https://arxiv.org/abs/2005.02950

Recommendations

• Scenario approximations of chance constraints
• Sensitivity Analysis for Simulations via Likelihood Ratios
• Scenario analysis via bundle decomposition
• Scenario simulation: Theory and methodology
• On Conditional Risk Assessments in Scenario Optimization
• Scenario generation with distribution functions and correlations
• Empirical likelihood based modal regression
• Modal simulation and visualization in finite mixture models
• Analysis of scenarios in the method of generalized interval estimations

zbMATH Keywords

modeconditional distributionunimodalityrisk allocationscenario analysisvariability measure

Mathematics Subject Classification ID

Actuarial mathematics (91G05) Applications of statistics to actuarial sciences and financial mathematics (62P05)

Cites Work

• Coherent measures of risk
• On Bayesian Modeling of Fat Tails and Skewness
• Modeling and Inference with v-Spherical Distributions
• Tail dependence for elliptically contoured distributions
• Asymptotic independence for unimodal densities
• Quantitative risk management. Concepts, techniques and tools
• Title not available (Why is that?)
• The estimation of the gradient of a density function, with applications in pattern recognition
• Heavy-Tail Phenomena
• The complete mixability and convex minimization problems with monotone marginal densities
• Comparison methods for stochastic models and risks
• Stochastic orders
• Stochastic finance. An introduction in discrete time.
• Values of Non-Atomic Games
• Classes of orderings of measures and related correlation inequalities. I. Multivariate totally positive distributions
• AN AXIOMATIC APPROACH TO CAPITAL ALLOCATION
• On a converse to Scheffé's theorem
• On a capital allocation by minimization of some risk indicators
• Tail Variance Premium with Applications for Elliptical Portfolio of Risks
• Title not available (Why is that?)
• Estimating value at risk of portfolio by conditional copula-GARCH method
• An optimization approach to the dynamic allocation of economic capital
• Log-concavity and strong log-concavity: a review
• Toward a copula theory for multivariate regular variation
• Classes of orderings of measures and related correlation inequalities. II. Multivariate reverse rule distributions
• \(\alpha\)-concave functions and measures and their applications
• Tail densities of skew-elliptical distributions
• On the Conditional Distribution of the Multivariate t Distribution
• A comprehensive approach to mode clustering
• An efficient approach to quantile capital allocation and sensitivity analysis
• Estimation of risk contributions with MCMC

Uses Software

• QRM

This page was built for publication: Modality for scenario analysis and maximum likelihood allocation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2657014)