An EM Algorithm for Double-Pareto-Lognormal Generalized Linear Model Applied to Heavy-Tailed Insurance Claims
نویسندگان
چکیده
Generalized linear models might not be appropriate when the probability of extreme events is higher than that implied by the normal distribution. Extending the method for estimating the parameters of a double Pareto lognormal distribution (DPLN) in Reed and Jorgensen (2004), we develop an EM algorithm for the heavy-tailed Double-Pareto-lognormal generalized linear model. The DPLN distribution is obtained as a mixture of a lognormal distribution with a double Pareto distribution. In this paper the associated generalized linear model has the location parameter equal to a linear predictor which is used to model insurance claim amounts for various data sets. The performance is compared with those of the generalized beta (of the second kind) and lognorma distributions.
منابع مشابه
Adaptive Premiums for Evolutionary Claims in Non-life Insurance
Rapid growth in heavy-tailed claim severity in commercial liability insurance requires insurer response by way of flexible mechanisms to update premiums. To this end in this paper a new premium principle is established for heavy-tailed claims, and its properties investigated. Risk-neutral premiums for heavy-tailed claims are consistently and unbiasedly estimated by the ratio of the first two ex...
متن کاملA self-calibrating method for heavy tailed data modeling : Application in neuroscience and finance
One of the main issues in the statistical literature of extremes concerns the tail index estimation, closely linked to the determination of a threshold above which a Generalized Pareto Distribution (GPD) can be fitted. Approaches to this estimation may be classified into two classes, one using standard Peak Over Threshold (POT) methods, in which the threshold to estimate the tail is chosen grap...
متن کاملPerformance analysis with truncated heavy–tailed distributions
This paper deals with queues and insurance risk processes where a generic service time, resp. generic claim, has the form U ∧K for some r.v. U with distribution B which is heavy–tailed, say Pareto or Weibull, and a typically large K, say much larger than EU . We study the compound Poisson ruin probability ψ(u) or, equivalently, the tail P(W > u) of the M/G/1 steady–state waiting time W . In the...
متن کاملQueues with Heavy - Tailed Service
We examine the performance and accuracy of simulating M/G/1 queues when the service time is Pareto distributed with shape parameter, alpha, between one and three. Two applications of this problem are in insurance risk and telecommunications. When 2 < alpha <= 3, the theoretical distribution of the sample averages of the queue waiting times is a stable distribution. When alpha <= 2, the mean wai...
متن کاملMultilevel Modeling of Insurance Claims Using Copulas
In property and casualty insurance, claims management is featured with modeling of semicontinuous insurance cost associated with individual risk transfer. This practice is further complicated by the multilevel structure of the insurance claims data, where a contract often contains a group of policyholders, each policyholder is insured under multiple types of coverage, and the contract is repeat...
متن کامل