The zero-adjusted log-symmetric quantile regression model applied to extramarital affairs data

TL;DR

This paper introduces a zero-adjusted log-symmetric quantile regression model that effectively handles zero-inflated data, demonstrated through an application to extramarital affairs data, with parameter estimation via maximum likelihood and validation through simulation.

Contribution

The paper presents a novel zero-adjusted log-symmetric distribution and integrates it into quantile regression, expanding modeling capabilities for zero-inflated data.

Findings

Successful application to real extramarital affairs data

Effective parameter estimation via maximum likelihood

Validation through Monte Carlo simulation

Abstract

In this work, we propose a zero-adjusted log-symmetric quantile regression model. Initially, we introduce zero-adjusted log-symmetric distributions, which allow for the accommodation of zeros. The estimation of the parameters is approached by the maximum likelihood method and a Monte Carlo simulation is performed to evaluate the estimates. Finally, we illustrate the proposed methodology with the use of a real extramarital affairs data set.