healthcare: Healthcare dataset

In dmarcondes/HGLD: Fit the Hurdle Generalized Lambda Distribution

Description

Dataset containing the healthcare expense of 129,257 customers of a Brazilian healthcare company between 2006 and 2009.

Usage

healthcare

Format

An object of class tbl_df (inherits from tbl, data.frame) with 289456 rows and 8 columns.

Details

The expenses are in Reais (Brazilian currency) and were deflated to the January 2006 value. In order to fit the models of the paper in the references it is necessary to truncate the expanses at R$ 100.

Value

ID	The ID of the customer.
sex	The sex of the customer.
age	The age of the customer on the considered year.
expense	The healthcare expense of the customer on the considered year.
log_expense	The logarithm of the healthcare expense of the customer on the considered year.
year	The considered year.
previous_expense	The healthcare expense of the customer on the previous year.
log_previous_expense	The logarithm of the healthcare expense of the customer on the previous year.

References

Marcondes, D.; Peixoto, C.; Maia, A. C.; A Survey of a Hurdle Model for Heavy-Tailed Data Based on the Generalized Lambda Distribution. (2017) arxiv1712.02183

dmarcondes/HGLD documentation built on May 28, 2019, 12:56 p.m.