Filippou, P; Marra, G; Radice, R; Zimmer, D; (2022) Estimating the Impact of Medical Care Usage on Work Absenteeism by a Trivariate Probit Model with Two Binary Endogenous Explanatory Variables. AStA Advances in Statistical Analysis 10.1007/s10182-022-00464-6. (In press).

Preview

Text Marra_Estimating the Impact of Medical Care Usage on Work Absenteeism by a Trivariate Probit Model with Two Binary Endogenous Explanatory Variables_AAM.pdf Download (193kB) | Preview

Abstract

The aim of this paper is to estimate the effects of seeking medical care on missing work. Specifically, our case study explores the question: Does visiting a medical provider cause an employee to miss work? To address this, we employ a model that can consistently estimate the impacts of two endogenous binary regressors. The model is based on three equations connected via a multivariate Gaussian distribution, which makes it possible to model the correlations among the equations, hence accounting for unobserved heterogeneity. Parameter estimation is reliably carried out via a trust region algorithm with analytical derivative information. We find that, observationally, having a curative visit associates with a nearly 80% increase in the probability of missing work, while having a preventive visit correlates with a smaller 13% increase in the likelihood of missing work. However, after addressing potential endogeneity, neither type of visit appears to significantly relate to missing work. That finding also applies to visits that occur during the previous year. Therefore, we conclude that the observed links between medical usage and absenteeism derive from unobserved heterogeneity, rather than direct causal channels. The modeling framework is available through the R package GJRM.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item