Description
Book SynopsisHow should planners use the available evidence to choose treatments? This book addresses key aspects of this question, exploring and partially resolving pervasive problems of identification and statistical inference that arise when studying treatment response and making treatment choices.
Trade Review"The book's strength lies in its complete presentation, up to this point, of the research in this area, and identification of the central areas of the problem (selection and sample data) that make the problem challenging. In addition, and perhaps most importantly, the book unites relevant research in a coherent and logical way that will serve interested researchers well."--Ben Alamar, Journal of the American Statistical Association
Table of ContentsPreface vii Chapter 1: Utilitarian Treatment of Heterogeneous Populations 1 1.1 Studying Treatment Response to Inform Treatment Choice 1 1.2 The Planning Problem 3 1.3 Practices that Limit the Usefulness of Research on Treatment Response 11 Chapter 2: The Selection Problem 19 2.1 Treatment Choice Using the Empirical Evidence Alone 20 2.2 Monotone Treatment Response 37 2.3 Exclusion Restrictions 49 Chapter 3: Treatment Using Experimental Data 56 3.1 The Expected Welfare (Risk) of a Statistical Treatment Rule 56 3.2 Using a Randomized Experiment to Evaluate an Innovation 62 3.3 Using Covariate Information with Data from a Randomized Experiment 74 Chapter 4: The Selection Problem with Sample Data 108 4.1 Sample-Analog Rules Using the Empirical Evidence Alone 109 References 115
