Abstract
All developed countries are facing the problem of providing affordable and high quality healthcare in recent years. This is due to the combination of an ageing population and the technological advancement in health science which leads to an increased life expectancy. This will affect the future use of hospital inpatient and outpatient services which in turn will place a significant stress on the economy since most medical services for the elderly are apportioned and funded under a national system. Thus, understanding the demand for healthcare and other key factors influencing the demand is crucial to better serve citizens. Hospital admission is considered to be a key proxy of the demand for healthcare, especially in the context of ageing populations as experienced globally. However, modeling hospital admissions, although very important, is often complicated by zero-inflation, by the covariates with time-varying effects, and by the necessity of borrowing information across individuals. Additionally, the rate of hospital admissions might differ between the group of individuals who have been hospitalized before and the group yet to be hospitalized. Also when individuals are clustered based on their baseline self-assessed health status, the distribution of hospital admissions and its relation to predictors may be quite different across and within different groups. In this paper we propose a unified Bayesian dynamic hurdle model which accommodates these features of the data in a semi-parametric approach. We analyze the data collected by the United States Health and Retirement Study in which the rate of hospital admissions varies across different self-assessed health groups. Simulation studies are performed for assessing the usefulness of the proposed model.
Similar content being viewed by others
References
Adams P, Hurd MD, McFadden D, Merrill A, Ribeiro T (2003) Healthy, wealthy, and wise? Tests for direct causal paths between health and socioeconomic status. J Econ 112:3–56
Albert JH, Chib S (1993) Bayesian analysis of binary and polychotomous response data. J Am Stat Assoc 88:669–679
Ando A, Modigliani F (1963) The “life cycle” hypothesis of saving: aggregate implications and tests. Am Econ Rev 53:55–84
Atella V, Deb P (2008) Are primary care physicians, public and private sector specialists substitutes or complements? Evidence from a simultaneous equations model for count data. J Health Econ 27:770–785
Baetschmann G, Winkelman R (2016) A dynamic hurdle model for zero-inflated count data. Commun Stat-Theory Methods 46:7174–7187
Banerjee R, Ziegenfus JY, Shah ND (2010) Impact of discontinuity in health insurance on resource utilization. BMC Health Serv Res 10:1–10
Biswas J, Das K (2019) A Bayesian approach of analysing semi-continuous longitudinal data with monotone missingness. Stat Modell 20:148–170
Biswas J, Das K (2021) A Bayesian quantile regression approach to multivariate semi-continuous longitudinal data. Comput Stat 36:241–260
Biswas J, Ghosh P, Das K (2020) A semi-parametric quantile regression approach to zero-inflated and incomplete longitudinal outcomes. Adv Stat Anal 104:261–283
Brant R (1990) Assessing proportionality in the proportional odds model for ordinal logistic regression. Biometrics 46:1171–1178
Brown S, Taylor K, Price SW (2005) Debt and distress: evaluating the psychological cost of credit. J Econ Psychol 26:642–663
Carroll KJ (2003) On the use and utility of the Weibull model in the analysis of survival data. Control Clin Trials 24:682–701
Celeux G, Forbes F, Robert CP, Titterington DM (2006) Deviance information criteria for missing data models. Bayesian Anal 1:651–673
Chatterjee A, Venkateswaran P, Das K (2016) Simultaneous state estimation for clustered based wireless sensor networks. IEEE Trans Wirel Commun 15:7985–7995
Daniels MJ, Hogan JW (2008) Missing data in longitudinal studies: strategies for Bayesian modeling and sensitivity analysis. CRC Press, New York
Das K (2016) A semiparametric Bayesian approach for joint modeling of longitudinal trait and event time. J Appl Stat 43:2850–2865
Das K, Daniels MJ (2014) A semiparametric approach to simultaneous covariance estimation for bivariate sparse longitudinal data. Biometrics 70:33–43
Das K, Ghosh P, Daniels MJ (2021) Modeling multiple time-varying related groups: a dynamic hierarchical Bayesian approach with an application to the health and retirement study. J Am Stat Assoc 116:558–568
Deb P, Trivedi PK (1997) Demand for medical care by the elderly: a finite mixture approach. J Appl Econ 12:313–336
Drentea P, Lavrakas PJ (2000) Over the limit: the association among health, race and debt. Soc Sci Med 50:517–529
Duan N, Manning WG, Morris CN, Newhouse JP (1983) A comparison of alternative models for the demand for medical care. J Bus Econ Stat 1:115–126
Dunson D, Xue Y, Carin L (2008) The matrix stick-breaking process: flexible Bayes meta-analysis. J Am Stat Assoc 103:317–327
Gelfand AE, Dey D, Chang H (1992) Model determination using predictive distributions with implementation via sampling based methods (with discussion). Bayesian Stat 4:147–167
Hurd M, Kapteyn A (2003) Health, wealth, and the role of institutions. J Hum Resour 3:386–415
Idler EL, Benyamini Y (1997) Self-rated health and mortality: a review of twenty-seven community studies. J Health Soc Behav 38:21–37
Ishwaran H, James LF (2002) Approximate Dirichlet process computing in finite normal mixtures. J Comput Graph Stat 11:508–532
McCullagh P (1980) Regression models for ordinal data. J R Stat Soc Ser B (Methodol) 42:109–127
Michaud PC, Van Soest A (2008) Health and wealth of elderly couples: causality tests using dynamic panel data models. J Health Econ 27:1312–1325
Mukherji A, Roychoudhury S, Ghosh P, Brown S (2016) Estimating health demand for an aging population: a flexible and robust Bayesian joint model. J Appl Econ 31:1140–1158
Park T, Casella G (2008) The Bayesian Lasso. J Am Stat Assoc 103:681–686
Pelkowski JM, Berger MC (2004) The impact of health on employment, wages, and hours worked over the life cycle. Q Rev Econ Finance 44:102–121
Ruppert D, Wand MP, Carroll RJ (2003) Semiparametric regression. Cambridge University Press, New York
United Nations Department of Economic and Social Affairs: Population Division (2015) World Population Aging 2015. United Nations, New York
Westbury LD, Syddall HE, Simmonds SJ, Cooper C, Aihie Sayer A (2016) Identification of risk factors for hospital admission using multiple-failure survival models: a toolkit for researchers. BMC Med Res Methodol 1–8
Winkelmann R (2004) Health care reform and the number of doctor visits: an econometric analysis. J Appl Econ 19:455–472
World health statistics (2016) Monitoring health for the SDGs, sustainable development goals. World Health Organization. https://apps.who.int/iris handle/10665/206498
Zhang Z (2016) Parametric regression model for survival data: Weibull regression model as an example. Ann Transl Med 4:484
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.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Das, K., Pareek, B., Brown, S. et al. A semi-parametric Bayesian dynamic hurdle model with an application to the health and retirement study. Comput Stat 37, 837–863 (2022). https://doi.org/10.1007/s00180-021-01143-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-021-01143-x