Results 1 - 10
of
33
Subexponential Distributions
, 1997
"... We survey the properties and uses of the class of subexponential probability distributions, paying particular attention to their use in modelling heavy-tailed data such as occurs in insurance and queueing applications. We give a detailed summary of the core theory and discuss subexponentiality in va ..."
Abstract
-
Cited by 38 (7 self)
- Add to MetaCart
We survey the properties and uses of the class of subexponential probability distributions, paying particular attention to their use in modelling heavy-tailed data such as occurs in insurance and queueing applications. We give a detailed summary of the core theory and discuss subexponentiality in various contexts including extremes, random walks and L'evy processes with negative drift, and sums of random variables, the latter extended to cover random sums, weighted sums and moving averages. 1. Definition and first properties Subexponential distributions are a special class of heavy--tailed distributions. The name arises from one of their properties, that their tails decrease more slowly than any exponential tail; see (1.4). This implies that large values can occur in a sample with non--negligible probability, and makes the subexponential distributions candidates for modelling situations where some extremely large values occur in a sample compared to the mean size of the data. Such a p...
Asymptotic results for the sum of dependent non-identically distributed random variables, Methodology and Computing
- in Applied Probability. Forthcoming. DOI
, 2008
"... In this paper we extend some results about the probability that the sum of n dependent subexponential random variables exceeds a given threshold u. In particular, the case of non-identically distributed and not necessarily positive random variables is investigated. Furthermore we establish criteria ..."
Abstract
-
Cited by 25 (1 self)
- Add to MetaCart
(Show Context)
In this paper we extend some results about the probability that the sum of n dependent subexponential random variables exceeds a given threshold u. In particular, the case of non-identically distributed and not necessarily positive random variables is investigated. Furthermore we establish criteria how far the tail of the marginal distribution of an individual summand may deviate from the others so that it still influences the asymptotic behavior of the sum. Finally we explicitly construct a dependence structure for which, even for regularly varying marginal distributions, no asymptotic limit of the tail sum exists. Some explicit calculations for diagonal copulas and t-copulas are given. 1
Delay bounds in communication networks with heavy-tailed and self-similar traffic
- IEEE Transactions on Information Theory
, 2012
"... Traffic with self-similar and heavy-tailed characteristics has been widely reported in communication networks, yet, the state-of-the-art of analytically predicting the delay performance of such networks is lacking. We address a particularly difficult type of heavy-tailed traffic where only the first ..."
Abstract
-
Cited by 12 (3 self)
- Add to MetaCart
(Show Context)
Traffic with self-similar and heavy-tailed characteristics has been widely reported in communication networks, yet, the state-of-the-art of analytically predicting the delay performance of such networks is lacking. We address a particularly difficult type of heavy-tailed traffic where only the first moment can be computed, and present nonasymptotic end-to-end delay bounds for such traffic. The derived performance bounds are non-asymptotic in that they do not assume a steady state, large buffer, or many sources regime. The analysis follows a network calculus approach where traffic is characterized by envelope functions and service is described by service curves. Our analysis considers a multi-hop path of fixed-capacity links with heavy-tailed self-similar cross traffic at each node. A key contribution of the analysis is a novel probabilistic sample-path bound for heavy-tailed arrival and service processes, which is based on a scale-free sampling method. We explore how delays scale as a function of the length of the path, and compare them with lower bounds. A comparison with simulations illustrates pitfalls when simulating self-similar heavy-tailed traffic, providing further evidence for the need of analytical bounds. I.
Pricing catastrophe insurance products based on actually reported claims
, 1998
"... Abstract This paper deals with the problem of pricing a financial product relying on an index of reported claims from catastrophe insurance. The problem of pricing such products is that, at a fixed time in the trading period, the total claim amount from the catastrophes occurred is not known. There ..."
Abstract
-
Cited by 10 (1 self)
- Add to MetaCart
(Show Context)
Abstract This paper deals with the problem of pricing a financial product relying on an index of reported claims from catastrophe insurance. The problem of pricing such products is that, at a fixed time in the trading period, the total claim amount from the catastrophes occurred is not known. Therefore, one has to price these products solely from knowing the aggregate amount of the reported claims at the fixed time point. This paper will propose a way to handle this problem, and will thereby extend the existing pricing models for products of this kind.
Large deviations for heavy-tailed random sums in compound renewal
"... Abstract In the present paper we investigate the precise large deviations for heavy-tailed random sums. First, we obtain a result which improves the relative result in Kl uppelberg and Mikosch (J. Appl. Probab. 34 (1997) 293). Then we introduce a more realistic risk model than classical ones, named ..."
Abstract
-
Cited by 8 (1 self)
- Add to MetaCart
Abstract In the present paper we investigate the precise large deviations for heavy-tailed random sums. First, we obtain a result which improves the relative result in Kl uppelberg and Mikosch (J. Appl. Probab. 34 (1997) 293). Then we introduce a more realistic risk model than classical ones, named the compound renewal model, and establish the precise large deviations in this model. c 2001 Elsevier Science B.V. All rights reserved MSC: primary 60F10; 60F05; 60G50; secondary 60K10; 62P05
Pricing Insurance Derivatives, the Case of CAT-Futures
- Risk, George State University Atlanta, Society of Actuaries, Monograph
, 1997
"... Since their appearance on the market, catastrophe insurance futures have triggered a considerable interest from both practitioners as well as academics. As one example of a securitized (re)insurance risk, its pricing and hedging contains many of the key problems to be addressed in the analysis of mo ..."
Abstract
-
Cited by 8 (1 self)
- Add to MetaCart
Since their appearance on the market, catastrophe insurance futures have triggered a considerable interest from both practitioners as well as academics. As one example of a securitized (re)insurance risk, its pricing and hedging contains many of the key problems to be addressed in the analysis of more general insurance de-rivatives. In the present paper we review the main methodological questions underlying the theoretical pricing of such products. We discuss utility maximi-zation pricing more in detail. A key methodological feature is the theory of incomplete markets. Our paper follows closely the exposition given in Meister (1995). Catastrophe Insurance Futures
RUIN PROBABILITIES FOR RISK PROCESSES WITH NON-STATIONARY ARRIVALS AND SUBEXPONENTIAL CLAIMS
"... Abstract. In this paper, we obtain the finite-horizon and infinite-horizon ruin probability asymptotics for risk processes with claims of subexponential tails for non-stationary arrival processes that satisfy a large deviation principle. As a result, the arrival process can be dependent, non-station ..."
Abstract
-
Cited by 6 (6 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper, we obtain the finite-horizon and infinite-horizon ruin probability asymptotics for risk processes with claims of subexponential tails for non-stationary arrival processes that satisfy a large deviation principle. As a result, the arrival process can be dependent, non-stationary and nonrenewal. We give three examples of non-stationary and non-renewal point processes: Hawkes process, Cox process with shot noise intensity and selfcorrecting point process. We also show some aggregate claims results for these three examples. Let us consider a classical risk model
Heavy Tails of Discounted Aggregate Claims in the Continuous-time Renewal Model
, 2007
"... We study the tail behavior of discounted aggregate claims in a continuous-time renewal model. For the case of Pareto-type claims, we establish a tail asymptotic formula, which holds uniformly in time. ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
We study the tail behavior of discounted aggregate claims in a continuous-time renewal model. For the case of Pareto-type claims, we establish a tail asymptotic formula, which holds uniformly in time.
Approximating the moments of marginals of high dimensional distributions, Annals of Probability, to appear
- Department of Mathematics, University of Michigan
"... For probability distributions on R n, we study the optimal sample size N = N(n, p) that suffices to uniformly approximate the pth moments of all one-dimensional marginals. Under the assumption that the marginals have bounded 4p moments, we obtain the optimal bound N = O(n p/2) for p>2. This bound ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
For probability distributions on R n, we study the optimal sample size N = N(n, p) that suffices to uniformly approximate the pth moments of all one-dimensional marginals. Under the assumption that the marginals have bounded 4p moments, we obtain the optimal bound N = O(n p/2) for p>2. This bound goes in the direction of bridging the two recent results: a theorem of Guedon and Rudelson [Adv. Math. 208 (2007) 798–823] which has an extra logarithmic factor in the sample size, and a result of Adamczak et al. [J. Amer. Math. Soc. 23 (2010) 535–561] which requires stronger subexponential moment assumptions. 1. Introduction. 1.1. The estimation problem. We study the following problem: how well can one approximate one-dimensional marginals of a distribution on Rn by sampling? Consider a random vector X in Rn, and suppose we would like to compute the pth moments of the marginals 〈X, x 〉 for all x ∈ Rn. To this end, we sample N
