Aggregate Markov models in life insurance: estimation via the EM algorithm

DOI10.1080/03461238.2023.2277786MaRDI QIDQ6587492zbMATH OpenFDO

Authors Jamaal Ahmad, Mogens Bladt

Publication date 14 August 2024

Published in Scandinavian Actuarial Journal (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/03461238.2023.2277786

Mathematics Subject Classification ID

Applications of continuous-time Markov processes on discrete state spaces (60J28) Markov processes: estimation; hidden Markov models (62M05) Applications of statistics to actuarial sciences and financial mathematics (62P05) Actuarial mathematics (91G05)

Review text

The authors do provide a complete algorithmic approach on life insurance modeling, using Markovian processes relying on the states of the individuals being insured in every time moment. For this purpose they assume a set of endogenous variables, which is relative to the updating of the model across time.

Recommendations

• Aggregate Markov models in life insurance: properties and valuation
• An algorithm evaluating generalized life insurance programs
• Estimation of the parameters of a Markov-modulated loss process in insurance
• Scenario-based life insurance prognoses in a multi-state Markov model
• A Markov process interest and mortality model

Cites work

• A survey of product-integration with a view toward application in survival analysis
• Aggregate Markov models in life insurance: properties and valuation
• An EM algorithm for batch Markovian arrival processes and its comparison to a simpler estimation procedure
• Cash flows and policyholder behaviour in the semi-Markov life insurance setup
• Fitting inhomogeneous phase‐type distributions to data: the univariate and the multivariate case
• scientific article; zbMATH DE number 4042996 (Why is no real title available?)
• scientific article; zbMATH DE number 1183924 (Why is no real title available?)
• scientific article; zbMATH DE number 1904082 (Why is no real title available?)
• scientific article; zbMATH DE number 3315741 (Why is no real title available?)
• Inhomogeneous phase-type distributions and heavy tails
• Introduction to Matrix Analytic Methods in Stochastic Modeling
• Joint lifetime modeling with matrix distributions
• Multistate models in health insurance
• Parameter estimation for Markov modulated poisson processes
• Phase-type mixture-of-experts regression for loss severities
• Renewal processes of phase type
• Reserves in Life and Pension Insurance
• Statistical models based on counting processes
• Survival and event history analysis. A process point of view
• The estimation of phase-type related functionals using Markov chain Monte Carlo methods

Cited in

(2)

• Aggregate Markov models in life insurance: properties and valuation
• Bivariate phase-type distributions for experience rating in disability insurance

This page was built for publication: Aggregate Markov models in life insurance: estimation via the EM algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587492)