Robust statistical modeling using the Birnbaum-Saunders-t distribution applied to insurance

Gilberto A. Paula, VICTOR ELISEO LEIVA SANCHEZ, Michelli Barros, Shuangzhe Liu

Research output: Contribution to journalArticlepeer-review

74 Scopus citations

Abstract

In this paper, we carry out robust modeling and influence diagnostics in Birnbaum-Saunders (BS) regression models. Specifically, we present some aspects related to BS and log-BS distributions and their generalizations from the Student-t distribution, and develop BS-t regression models, including maximum likelihood estimation based on the EM algorithm and diagnostic tools. In addition, we apply the obtained results to real data from insurance, which shows the uses of the proposed model.

Original languageEnglish
Pages (from-to)16-34
Number of pages19
JournalApplied Stochastic Models in Business and Industry
Volume28
Issue number1
DOIs
StatePublished - 1 Jan 2012

Keywords

  • EM algorithm
  • generalized Birnbaum-Saunders and sinh-normal distributions
  • influence diagnostics
  • likelihood methods
  • log-linear models
  • robustness

Fingerprint Dive into the research topics of 'Robust statistical modeling using the Birnbaum-Saunders-t distribution applied to insurance'. Together they form a unique fingerprint.

Cite this