Methodologies for observational studies of health care policy / Mike Baiocchi.

Format:

Book

Manuscript

Thesis/Dissertation

Author/Creator:

Baiocchi, Michael.

Contributor:

Small, Dylan, advisor.

University of Pennsylvania.

Language:

English

Subjects (All):

Penn dissertations--Managerial Science and Applied Economics.

Health care management and economics--Penn dissertations.

Penn dissertations--Managerial science and applied economics.

Managerial science and applied economics--Penn dissertations.

Local Subjects:

Penn dissertations--Managerial Science and Applied Economics.

Health care management and economics--Penn dissertations.

Penn dissertations--Managerial science and applied economics.

Managerial science and applied economics--Penn dissertations.

Physical Description:

ix, 69 pages ; 29 cm

Production:

2011.

Summary:

This dissertation is separated into three chapters. Each chapter develops a methodology. These methodologies are appropriate for observational studies and were motivated by questions arising from health care policy. The first study is motivated by research on the regionalization of neonatal intensive care units. This study develops a matching-based approach to instrumental variables. The second study is motivated by a study of the association between a patient's body mass index and the amount of time spent in surgery. In this study we develop the statistical properties of an optimal full matching algorithm for a nonbipartite setting. The third chapter lays groundwork for future methodologies. In this chapter we propose a disciplined way of combining prognostic score matching with propensity score matching.

Notes:

Adviser: Dylan Small.

Thesis (Ph.D. in Managerial Science and Applied Economics) -- University of Pennsylvania, 2011.

Includes bibliographical references.