Files

Abstract

The analysis of the total amount of expenses for medical services of an individual during a given year can be divided into two parts: the analysis of the probability of having non-zero expenses, and the analysis of the amount of the non-zero expenses. In this paper we construct a statistical model for the total amount of expenses for medical services. First, we analyse which factors influence the probability of having non-zero expenses on the basis of a logit model. Second, we analyse ten probability distributions that might be used to describe the amount of the non-zero expenses, where we distinguish five categories of non-zero expenses. Third, we examine which factors influence the parameters of the probability distribution of the amount of non-zero expenses of three categories on the basis of a lognormal model. The models are applied to Dutch health insurance data.

Details

PDF

Statistics

from
to
Export
Download Full History