CMPH: a multivariate phase-type aggregate loss distribution

Ren Jiandong () and Zitikis Ricardas ()
Additional contact information
Ren Jiandong: Department of Statistical and Actuarial Sciences, Western University, London, Ontario N6A 5B7, Canada
Zitikis Ricardas: School of Mathematical and Statistical Sciences, Western University, London, Ontario N6A 5B7, Canada

Dependence Modeling, 2017, vol. 5, issue 1, 304-315

Abstract: We introduce a compound multivariate distribution designed for modeling insurance losses arising from different risk sources in insurance companies. The distribution is based on a discrete-time Markov Chain and generalizes the multivariate compound negative binomial distribution, which is widely used for modeling insurance losses.We derive fundamental properties of the distribution and discuss computational aspects facilitating calculations of risk measures of the aggregate loss, as well as allocations of the aggregate loss to individual types of risk sources. Explicit formulas for the joint moment generating function and the joint moments of different loss types are derived, and recursive formulas for calculating the joint distributions given. Several special cases of particular interest are analyzed. An illustrative numerical example is provided.

Keywords: multivariate distribution; compound distribution; Markov chain; risk measure; risk allocation (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/demo-2017-0018 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:vrs:demode:v:5:y:2017:i:1:p:304-315:n:18

DOI: 10.1515/demo-2017-0018

Access Statistics for this article

Dependence Modeling is currently edited by Giovanni Puccetti

More articles in Dependence Modeling from De Gruyter
Bibliographic data for series maintained by Peter Golla ().