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.
Similar content being viewed by others
References
Abadie, A., Drukker, D., Herr, J.L., Imbens, G.W.: Implementing matching estimators for average treatment effects in Stata. Stata J. 4, 290–311 (2004)
Angrist, J.D., Imbens, G.W., Rubin, D.B.: Identification of causal effects using instrumental variables. J. Am. Stat. Assoc. 91(434), 444–455 (1996)
Ashford, J., Sowden, R.: Multi-variate probit analysis. Biometrics 26, 535–546 (1970)
Cappellari, L., Jenkins, S.P.: Multivariate probit regression using simulated maximum likelihood. Stata J. 3, 278–294 (2003)
Chib, S., Greenberg, E.: Analysis of multivariate probit models. Biometrika 85, 347–361 (1998)
Chib, S., Greenberg, E.: Semiparametric modeling and estimation of instrumental variable models. J. Comput. Graph. Stat. 16(1), 86–114 (2007)
Filippou, P., Kneib, T., Marra, G., Radice, R.: A trivariate additive regression model with arbitrary link functions and varying correlation matrix. J. Stat. Plan. Inference 199, 236–248 (2019)
Filippou, P., Marra, G., Radice, R.: Penalized likelihood estimation of a trivariate additive probit model. Biostatistics 18(3), 569–585 (2017)
Gould, E.: Decomposing the effects of children’s health on mother’s labor supply: Is it time or money? Health Econ. 13, 525–541 (2004)
Henningsen, A.: mvProbit: multivariate probit models. R package version 0.1-10 (2021)
Little, R.J.A.: A note about models for selectivity bias. Econometrica 53(6), 1469–1474 (1985)
Marra, G., Radice, R.: Estimation of a semiparametric recursive bivariate probit model in the presence of endogeneity. Can. J. Stat. 39, 259–279 (2011)
Marra, G., Radice, R.: GJRM: generalized joint regression modeling. R package version 0.2-6. https://cran.r-project.org/package=GJRM (2022)
Nicholson, S., Pauly, M., Polsky, D., et al.: Measuring the effects of workloss on productivity with team production. Health Econ. 15, 111–123 (2006)
Pauly, M., Nicholson, S., Polsky, D., et al.: Valuing reductions in on-the-job illness: ‘presenteeism’ from managerial and economic perspectives. Health Econ. 17, 469–485 (2008)
Schultz, A., Chen, C., Edington, D.: The cost and impact of health conditions on presenteeism to employers a review of the literature. Pharmacoeconomics 27, 365–378 (2009)
Strömberg, C., Aboagye, E., Hagberg, J., Bergström, G., Lohela-Karlsson, M.: Estimating the effect and economic impact of absenteeism, presenteeism, and work environment-related problems on reductions in productivity from a managerial perspective. Value Health 20, 1058–1064 (2017)
Varian, H.: Microeconomic Analysis, 3rd edn. W.W. Norton and Company, New York (1992)
Wilde, J.: Identification of multiple equation probit models with endogenous dummy regressors. Econ. Lett. 69(3), 309–312 (2000)
Zhang, W., Bansback, N., Anis, A.: Measuring and valuing productivity loss due to poor health: a critical review. Soc. Sci. Med. 72, 185–192 (2011)
Zhang, W., Sun, H., Woodcock, S., Anis, A.: Illness related wage and productivity losses: valuing ‘presenteeism. Soc. Sci. Med. 147, 62–71 (2015)
Acknowledgements
The first two authors were supported by the Engineering and Physical Sciences Research Council [EP/T033061/1].
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Code to simulate data and estimate trivariate binary models.
For the case without instrument, v3 is dropped from the equations above. To allow the error terms to be Student’s t (with two degrees of freedom) or \(\chi ^2\) (with two degrees of freedom) distributed, respectively, the above R code was be easily modified by replacing
with
or with
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Filippou, P., Marra, G., Radice, R. et al. Estimating the Impact of Medical Care Usage on Work Absenteeism by a Trivariate Probit Model with Two Binary Endogenous Explanatory Variables. AStA Adv Stat Anal 107, 713–731 (2023). https://doi.org/10.1007/s10182-022-00464-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10182-022-00464-6