ArticlePDF Available

Diversification in heavy-tailed portfolios: properties and pitfalls

Authors:

Abstract and Figures

We discuss risk diversification in multivariate regularly varying models and provide explicit formulas for Value-at-Risk asymptotics in this case. These results allow us to study the influence of the portfolio weights, the overall loss severity, and the tail dependence structure on large portfolio losses. We outline sufficient conditions for the sub- and superadditivity of the asymptotic portfolio risk in multivariate regularly varying models and discuss the case when these conditions are not satisfied. We provide several examples to illustrate the resulting variety of diversification effects and the crucial impact of the tail dependence structure in infinite mean models. These examples show that infinite means in multivariate regularly varying models do not necessarily imply negative diversification effects. This implication is true if there is no loss-gain compensation in the tails, but not in general. Depending on the loss-gain compensation, asymptotic portfolio risk can be subadditive, superadditive, or neither.
Content may be subject to copyright.
A preview of the PDF is not available
... This topic has already been investigated in the literature; see e.g. Basrak et al. (2002), Barbe et al. (2006), Mainik and Embrechts (2013), and Cuberos et al. (2015). For instance, assuming X multivariate regularly varying, X ∈ MRV −α (b, ν) (as defined in Definition A.5, Appendix A.1), implies that the sum S d ∈ RV −α (b). ...
Preprint
Full-text available
We build a sharp approximation of the whole distribution of the sum of iid heavy-tailed random vectors, combining mean and extreme behaviors. It extends the so-called 'normex' approach from a univariate to a multivariate framework. We propose two possible multi-normex distributions, named $d$-Normex and MRV-Normex. Both rely on the Gaussian distribution for describing the mean behavior, via the CLT, while the difference between the two versions comes from using the exact distribution or the EV theorem for the maximum. The main theorems provide the rate of convergence for each version of the multi-normex distributions towards the distribution of the sum, assuming second order regular variation property for the norm of the parent random vector when considering the MRV-normex case. Numerical illustrations and comparisons are proposed with various dependence structures on the parent random vector, using QQ-plots based on geometrical quantiles.
... The tail behavior of the aggregated risk based on multiple risk factors satisfying the MRV model can be explicitly derived (see, e.g., Hauksson et al. 2001; Barbe, Fougeres, and Genest 2006;Embrechts, Lambrigger, and Wüthrich 2009). Furthermore, portfolio diversification under the MRV model was investigated in Mainik and Rüschendorf (2010), Zhou (2010), and Mainik and Embrechts (2013), among others. Besides the applications in finance and insurance, the MRV model is also applied in telecommunications networks (see, e.g., Resnick and Samorodnitsky 2015;Samorodnitsky et al. 2016). ...
Article
Full-text available
In this paper, we propose a test for the multivariate regular variation model. The test is based on testing whether the extreme value indices of the radial component conditional on the angular component falling in different subsets are the same. Combining the test on the constancy across extreme value indices in different directions with testing the regular variation of the radial component, we obtain the test for testing multivariate regular variation. Simulation studies demonstrate the good performance of the proposed tests. We apply this test to examine two data sets used in previous studies that are assumed to follow the multivariate regular variation model.
... The copula for factors with comonotonic dependence must be the upper Fréchet bound. Interestingly, there are cases where independence results in a worse (larger) VaR restimate than under comonotonicity (Mainik and Embrechts 2013). The point stressed by Embrechts et al. (2013) is that the comonotonic copula is not typically the solution for Equation (10). ...
Article
Full-text available
The federal crop insurance program covered more than 110 billion dollars in total liability in 2018. The program consists of policies across a wide range of crops, plans, and locations. Weather and other latent variables induce dependence among components of the portfolio. Computing value-at-risk (VaR) is important because the Standard Reinsurance Agreement (SRA) allows for a portion of the risk to be transferred to the federal government. Further, the international reinsurance industry is extensively involved in risk sharing arrangements with U.S. crop insurers. VaR is an important measure of the risk of an insurance portfolio. In this context, VaR is typically expressed in terms of probable maximum loss (PML) or as a return period, whereby a loss of certain magnitude is expected to return within a given period of time. Determining bounds on VaR is complicated by the non-homogeneous nature of crop insurance portfolios. We consider several different scenarios for the marginal distributions of losses and provide sharp bounds on VaR using a rearrangement algorithm. Our results are related to alternative measures of portfolio risks based on multivariate distribution functions and alternative copula specifications.
... Realistic estimates for credit risks and the possible losses, particularly of large portfolios are important not only for the creditors, also and maybe even more from a systemic viewpoint. There is a wealth of studies on credit risk (see (Bielecki and Rutkowski 2013;Bluhm et al. 2016;Chava et al. 2011;Crouhy et al. 2000;Duffie and Singleton 1999;Glasserman and Ruiz-Mata 2006;Heitfield et al. 2006;Lando 2009;Mainik and Embrechts 2013;McNeil et al. 2005;Schönbucher 2003) and references therein). For a review on credit contagion, see (Avkiran et al. 2018;Egloff et al. 2007;Weber 2004 2006;Hatchett and Kühn 2009), and, for studies on practical investment and Value-at-Risk applications of copula theory in evaluating systemic risk, see (Low et al. 2013;Low 2017). ...
Article
Full-text available
The stability of the financial system is associated with systemic risk factors such as the concurrent default of numerous small obligors. Hence, it is of utmost importance to study the mutual dependence of losses for different creditors in the case of large, overlapping credit portfolios. We analytically calculate the multivariate joint loss distribution of several credit portfolios on a non-stationary market. To take fluctuating asset correlations into account, we use an random matrix approach which preserves, as a much appreciated side effect, analytical tractability and drastically reduces the number of parameters. We show that, for two disjoint credit portfolios, diversification does not work in a correlated market. Additionally, we find large concurrent portfolio losses to be rather likely. We show that significant correlations of the losses emerge not only for large portfolios with thousands of credit contracts, but also for small portfolios consisting of a few credit contracts only. Furthermore, we include subordination levels, which were established in collateralized debt obligations to protect the more senior tranches from high losses. We analytically corroborate the observation that an extreme loss of the subordinated creditor is likely to also yield a large loss of the senior creditor.
... Better credit risk estimation is urgently called for. A variety of different approaches exists, see (Bielecki and Rutkowski 2013;Bluhm et al. 2016;Crouhy et al. 2000;Duffie and Singleton 1999;Glasserman and Ruiz-Mata 2006;Heitfield et al. 2006;Ibragimov and Walden 2007;Lando 2009;Mainik and Embrechts 2013;McNeil et al. 2005) for an overview. Most of them fall into the reduced-form (Chava et al. 2011;Duffie and Singleton 1999;Schönbucher 2003) or structural-approach class (Elizalde 2005;Merton 1974); a comprehensive review is given in (Giesecke 2004). ...
Article
Full-text available
We review recent progress in modeling credit risk for correlated assets. We employ a new interpretation of the Wishart model for random correlation matrices to model non-stationary effects. We then use the Merton model in which default events and losses are derived from the asset values at maturity. To estimate the time development of the asset values, the stock prices are used, the correlations of which have a strong impact on the loss distribution, particularly on its tails. These correlations are non-stationary, which also influences the tails. We account for the asset fluctuations by averaging over an ensemble of random matrices that models the truly existing set of measured correlation matrices. As a most welcome side effect, this approach drastically reduces the parameter dependence of the loss distribution, allowing us to obtain very explicit results, which show quantitatively that the heavy tails prevail over diversification benefits even for small correlations. We calibrate our random matrix model with market data and show how it is capable of grasping different market situations. Furthermore, we present numerical simulations for concurrent portfolio risks, i.e., for the joint probability densities of losses for two portfolios. For the convenience of the reader, we give an introduction to the Wishart random matrix model.
... Better credit risk estimation is urgently called for. A variety of different approaches exists, see [3,5,9,12,25,29,33,22,18,32] for an overview. Most of them fall into the reduced-form [12,7,50] or structural-approach class [34,13], a comprehensive review is given in [16]. ...
Article
We review recent progress in modeling credit risk for correlated assets. We start from the Merton model which default events and losses are derived from the asset values at maturity. To estimate the time development of the asset values, the stock prices are used whose correlations have a strong impact on the loss distribution, particularly on its tails. These correlations are non-stationary which also influences the tails. We account for the asset fluctuations by averaging over an ensemble of random matrices that models the truly existing set of measured correlation matrices. As a most welcome side effect, this approach drastically reduces the parameter dependence of the loss distribution, allowing us to obtain very explicit results which show quantitatively that the heavy tails prevail over diversification benefits even for small correlations. We calibrate our random matrix model with market data and show how it is capable of grasping different market situations. Furthermore, we present numerical simulations for concurrent portfolio risks, i.e., for the joint probability densities of losses for two portfolios. For the convenience of the reader, we give an introduction to the Wishart random matrix model.
... That means that average rainfall is less extreme than point rainfall if the marginals have finite expectation, as typically encountered in practice, and more extreme if they have infinite expectation. Mainik and Embrechts [2013] computed the corresponding coefficient θ ξ for ξ > 0. In this setup, X(s i ), i = 1, . . . , m, are interpreted as dependent, heavy-tailed risk factors, and θ ξ represents the diversification in the portfolio P = m i=1 c i X(s i ). ...
Article
The distribution of spatially aggregated data from a stochastic process $X$ may exhibit a different tail behavior than its marginal distributions. For a large class of aggregating functionals $\ell$ we introduce the $\ell$-extremal coefficient that quantifies this difference as a function of the extremal spatial dependence in $X$. We also obtain the joint extremal dependence for multiple aggregation functionals applied to the same process. Explicit formulas for the $\ell$-extremal coefficients and multivariate dependence structures are derived in important special cases. The results provide a theoretical link between the extremal distribution of the aggregated data and the corresponding underlying process, which we exploit to develop a method for statistical downscaling. We apply our framework to downscale daily temperature maxima in the south of France from a gridded data set and use our model to generate high resolution maps of the warmest day during the 2003 heatwave.
... During the past years many studies have pointed out the importance of better credit risk estimation and proposed different approaches, see Refs. [3,4,5,6,7,8,9,10,11] for an overview. ...
Article
In structural credit risk models, default events and the ensuing losses are both derived from asset values at maturity. Hence, it is of the utmost importance to choose a distribution for these asset values that is in accordance with empirical data. At the same time, it is desirable to still preserve some analytical tractability. We achieve both goals by putting forward an ensemble approach for asset correlations. Consistent with the data, we view them as fluctuating quantities for which we may choose the average correlation as homogeneous. Thereby, we can reduce the number of parameters to two, the average correlation between assets and the strength of the fluctuations around this average value. Yet, the resulting asset value distribution describes the empirical data well. This allows us to derive the distribution of credit portfolio losses. With Monte Carlo simulations for the value-at-risk and expected tail loss, we validate the assumptions of our approach and demonstrate the necessity of taking fluctuating correlations into account.
... The general properties of the optimization problem are discussed in Mainik and Rüschendorf [35], Mainik [32], and Mainik and Embrechts [34]. In particular, it is known that the function w → γ w is convex for α > 1. ...
Article
Using daily returns of the S&P 500 stocks from 2001 to 2011, we perform a backtesting study of the portfolio optimization strategy based on the extreme risk index (ERI). This method uses multivariate extreme value theory to minimize the probability of large portfolio losses. With more than 400 stocks to choose from, our study seems to be the first application of extreme value techniques in portfolio management on a large scale. The primary aim of our investigation is the potential of ERI in practice. The performance of this strategy is benchmarked against the minimum variance portfolio and the equally weighted portfolio. These fundamental strategies are important benchmarks for large-scale applications. Our comparison includes annualized portfolio returns, maximal drawdowns, transaction costs, portfolio concentration, and asset diversity in the portfolio. In addition to that we study the impact of an alternative tail index estimator. Our results show that the ERI strategy significantly outperforms both the minimum-variance portfolio and the equally weighted portfolio on assets with heavy tails.
Article
In this paper we work in the framework of a k -dimensional vector of log-linear risks. Under weak conditions on the marginal tails and the dependence structure of a vector of positive risks, we derive the asymptotic tail behaviour of the aggregated risk and present an application concerning log-normal risks with stochastic volatility.
Article
Full-text available
The notion of asymptotic portfolio loss order is introduced to compare multivariate stochastic risk models with respect to extreme portfolio losses. In the framework of multivariate regular variation comparison criteria are derived in terms of spectral measures. This allows for analytical and numerical verification in applications. Worst and best case dependence structures with respect to the asymptotic portfolio loss order are determined. Comparison criteria in terms of further stochastic ordering notions are derived. The examples include elliptical distributions and multivariate regularly varying models with Gumbel, Archimedean, and Galambos copulas. Particular interest is paid to the inverse influence of dependence on the diversification of risks with infinite expectations.
Article
Extremes Values, Regular Variation and Point Processes is a readable and efficient account of the fundamental mathematical and stochastic process techniques needed to study the behavior of extreme values of phenomena based on independent and identically distributed random variables and vectors. It presents a coherent treatment of the distributional and sample path fundamental properties of extremes and records. It emphasizes the core primacy of three topics necessary for understanding extremes: the analytical theory of regularly varying functions; the probabilistic theory of point processes and random measures; and the link to asymptotic distribution approximations provided by the theory of weak convergence of probability measures in metric spaces. The book is self-contained and requires an introductory measure-theoretic course in probability as a prerequisite. Almost all sections have an extensive list of exercises which extend developments in the text, offer alternate approaches, test mastery and provide for enjoyable muscle flexing by a reader. The material is aimed at students and researchers in probability, statistics, financial engineering, mathematics, operations research, civil engineering and economics who need to know about: * asymptotic methods for extremes; * models for records and record frequencies; * stochastic process and point process methods and their applications to obtaining distributional approximations; * pervasive applications of the theory of regular variation in probability theory, statistics and financial engineering. "This book is written in a very lucid way. The style is sober, the mathematics tone is pleasantly conversational, convincing and enthusiastic. A beautiful book!" ---Bulletin of the Dutch Mathematical Society "This monograph is written in a very attractive style. It contains a lot of complementary exercises and practically all important bibliographical reference." ---Revue Roumaine de Mathématiques Pures et Appliquées
Article
A statistical analysis which provides a risk assessment of nuclear safety based on historical data is conducted. Classical probabilistic models from risk theory are used to analyze data on nuclear power accidents from 1952 to 2011. Findings are that the severities of nuclear power accidents should be modeled with an infinite mean model and, thus, cannot be insured by an unlimited cover.
Article
We establish the equivalence between the multivariate regular variation of a random vector and the univariate regular variation of all linear combinations of the components of such a vector. According to a classical result of Kesten [Acta Math. 131 (1973) 207-248], this result implies that stationary solutions to multivariate linear stochastic recurrence equations are regularly varying. Since GARCH processes can be embedded in such recurrence equations their finite-dimensional distributions are regularly varying.