Dirichlet process mixture models for insurance loss data
Authors:
- 24 October 2017
- journal article
- research article
- Published by Taylor & Francis in Scandinavian Actuarial Journal
- Vol. 2018 (6) , 545-554
Abstract
In the recent insurance literature, a variety of finite-dimensional parametric models have been proposed for analyzing the hump-shaped, heavy-tailed, and highly skewed loss data often encountered in applications. These parametric models are relatively simple, but they lack flexibility in the sense that an actuary analyzing a new data-set cannot be sure that any one of these parametric models will be appropriate. As a consequence, the actuary must make a non-trivial choice among a collection of candidate models, putting him/herself at risk for various model misspecification biases. In this paper, we argue that, at least in cases where prediction of future insurance losses is the ultimate goal, there is reason to consider a single but more flexible nonparametric model. We focus here on Dirichlet process mixture models, and we reanalyze several of the standard insurance data-sets to support our claim that model misspecification biases can be avoided by taking a nonparametric approach, with little to no cost, compared to existing parametric approaches.Keywords
This publication has 35 references indexed in Scilit:
- Folded and log-folded-tdistributions as models for insurance loss dataScandinavian Actuarial Journal, 2011
- Kullback Leibler property of kernel mixture priors in Bayesian density estimationElectronic Journal of Statistics, 2008
- Posterior convergence rates of Dirichlet mixtures at smooth densitiesThe Annals of Statistics, 2007
- Modeling actuarial data with a composite lognormal-Pareto modelScandinavian Actuarial Journal, 2005
- Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densitiesThe Annals of Statistics, 2001
- Markov Chain Sampling Methods for Dirichlet Process Mixture ModelsJournal of Computational and Graphical Statistics, 2000
- Estimating Mixture of Dirichlet Process ModelsJournal of Computational and Graphical Statistics, 1998
- Bayesian Density Estimation and Inference Using MixturesJournal of the American Statistical Association, 1995
- Estimating normal means with a conjugate style dirichlet process priorCommunications in Statistics - Simulation and Computation, 1994
- On a Class of Bayesian Nonparametric Estimates: I. Density EstimatesThe Annals of Statistics, 1984