Bayesian Analysis of Loss Ratios Using the Reversible Jump Algorithm

TL;DR

This paper applies a reversible jump algorithm to select models for insurance loss ratios, demonstrating improvements over traditional methods through recent advances in reversible jump computation.

Contribution

It introduces enhancements to the reversible jump algorithm for better model discrimination in insurance loss ratio analysis.

Findings

Improved reversible jump algorithm performance

Effective model discrimination for insurance data

Enhanced computational efficiency

Abstract

In this paper we consider the problem of model choice for a set of insurance loss ratios. We use a reversible jump algorithm for our model discrimination and show how the vanilla reversible jump algorithm can be improved on using recent methodological advances in reversible jump computation.