Analyzing insurance data with an exponentiated composite Inverse-Gamma Pareto model

TL;DR

This paper introduces an exponentiated version of the Inverse Gamma-Pareto composite model, improving fit for insurance data and filling a gap in the application of exponentiated composite distributions.

Contribution

It proposes a novel exponentiated Inverse Gamma-Pareto model and demonstrates its superior goodness-of-fit over the one-parameter version on insurance datasets.

Findings

The two-parameter exponentiated model outperforms the one-parameter in fit.

The model provides a very good fit for multiple insurance datasets.

Exponentiated composite models are effective in insurance data modeling.

Abstract

Exponentiated models have been widely used in modeling various types of data such as survival data and insurance claims data. However, the exponentiated composite distribution models have not been explored yet. In this paper, we introduce an improvement of the one-parameter Inverse Gamma-Pareto composite model by exponentiating the random variable associated with the one-parameter Inverse Gamma-Pareto composite distribution function. The goodness-of-fit of the exponentiated Inverse Gamma-Pareto was assessed using three different insurance data sets. The two-parameter exponentiated Inverse Gamma-Pareto model outperforms the one-parameter Inverse Gamma-Pareto model in terms of goodness-of-fit measures for all datasets. In addition, the proposed exponentiated composite Inverse Gamma-Pareto model provides a very good fit with some well-known insurance datasets.