Models in hospital operations management and consumer choice in health care
- The topic of this dissertation is the development of data-driven methods and tools which may be used to aid policy makers and consumers in key healthcare decisions. Two specific problems are studied: one problem is in the hospital operations management, the other one is faced by consumers in the Marketplace. In both settings, new model and computational methods are developed to assist the decision maker in making an optimal decision. Chapter 2 presents a forecasting mechanism of operating room workload and dynamic adjustment policy on the staffing level decisions, which may be used by hospitals to better schedule the operating rooms. Staffing levels are usually determined months in advance when little information about the surgeries and their durations is known. This lack of information leads to a mismatch between the staffing level and the actual surgical duration, which results in excessive labor costs. This paper proposes a new dynamic staffing policy according to which hospital administrators adjust nurse staffing levels as information on the different types of surgeries arrives sequentially. The staffing level adjustments are accompanied with cost in order to incorporate the unwillingness to change. Using this dynamic framework, it is shown that a threshold policy defined by two adjustment levels is optimal. Numerical results using data from a large academic center suggest that the practical appeal of the dynamic policies will be greater where they will face the largest resistance: in hospitals where management considers dynamic labor adjustments to be impractical due to their complexity and thus implied costs. Chapter 3 begins the research on the impact of the Health Insurance Marketplace (the Marketplace) on consumers. The aim is to study the motivation behind the consumer choice and the roles that insurers and government play. It also provide insights in improving the efficiency in the Marketplace.This chapter introduces a cost point of view in modeling consumer decision. Consumers make rational choice by optimizing the objective function. The objective function includes the actual costs and the cost equivalent of health utilization. It is driven by the evidence that consumers value their costs most importantly. Moreover, this chapter presents a conceptual framework of dividing health utilization into regions. This captures the practical features such as over utilization in healthcare. Bounded rationality is also discussed and three potential directions are provided in this chapter. Chapter 4 builds a model to predict medical expenditure which consists of a regression, a transition, and an evolution of the parameters. This model is the first to use the number of service visits as predictors. This is consistent with the collecting process of data which is at an service event base. Moreover, it incorporates the behavior considerations of the different insurance status of consumers. Aside from this model, two alternatives models are considered for comparison. They reflect two existing approaches: regression on personal characteristics and log transformation for nonzero expenditures. The predictors are selected and their coefficients are evaluated using the longitudinal data from Medical Expenditure Panel Survey (MEPS). The two alternatives are compared with the model and it turns out that the model outperforms them in both prediction accuracy and variability explanation. Chapter 5 presents the simulation of consumer choice.The results suggest that the cost saver better matches the statistics from the federal government than the utility maximizer. Moreover, this chapter provides implications to the share between insurers and consumers. The actuarial values (the share of expenditure paid by insurers) is calculated based on simulated participation. They demonstrates inconsistency with the standard ones. Therefore inefficiency exits in the actuarial value calculation. This chapter also evaluates the government involvements in the Marketplace. The results suggest that its involvements, especially the government subsidies, effectively encourage the broader participation of insurance plans.
|Type of resource
|electronic; electronic resource; remote
|1 online resource.
|Stanford University, Graduate School of Business.
|Zenios, Stefanos A
|Zenios, Stefanos A
|Lee, Hau Leung
|Lee, Hau Leung
|Statement of responsibility
|Submitted to the Graduate School of Business.
|Thesis (Ph.D.)--Stanford University, 2015.
- © 2015 by Su Xie
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...