Risk measure estimation under two component mixture models with trimmed data

S. A. Abu Bakar, S. Nadarajah*

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    168 Downloads (Pure)

    Abstract

    Several two component mixture models from the transformed gamma and transformed beta families are developed to assess risk performance. Their common statistical properties are given and applications to real insurance loss data are shown. A new data trimming approach for parameter estimation is proposed using the maximum likelihood estimation method. Assessment with respect to Value-at-Risk and Conditional Tail Expectation risk measures are presented. Of all the models examined, the mixture of inverse transformed gamma-Burr distributions consistently provides good results in terms of goodness-of-fit and risk estimation in the context of the Danish fire loss data.

    Original languageEnglish
    Pages (from-to)835-852
    Number of pages18
    JournalJournal of Applied Statistics
    Volume46
    Issue number5
    Early online date3 Sept 2018
    DOIs
    Publication statusPublished - 4 Apr 2019

    Keywords

    • Danish fire loss data
    • heavy tailed distributions
    • mixture models
    • transformed gamma and transformed beta families

    Fingerprint

    Dive into the research topics of 'Risk measure estimation under two component mixture models with trimmed data'. Together they form a unique fingerprint.

    Cite this