Experience rating in the classic Markov chain life insurance setting: An empirical Bayes and multivariate frailty approach

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

We consider experience rating in the classic Markov chain life insurance setting.We focus on shrinkage estimation of group efects in an empirical Bayes and multivariate frailty extension, building on ideas from group life insurance and survivaland event history analysis. Within this framework, we provide insights regardingthe structure of the likelihoods and sufciency of summary statistics such as occurrences and exposures. Simple shrinkage estimators, given by well-known credibility formulas, are obtained under quadratic loss for mutually independent conjugateGamma priors. The applicability of these simple shrinkage estimators for disabilityinsurance is illustrated in a numerical example using simulated data.
OriginalsprogEngelsk
TidsskriftEuropean Actuarial Journal
ISSN2190-9733
DOI
StatusE-pub ahead of print - 2019

ID: 213502953