Suchergebnisse

Frontmatter -- Contents -- Preface -- Introduction -- I. Prediction with Incomplete Data -- 1. Conditional Prediction -- 2. Missing Outcomes -- 3. Instrumental Variables -- 4. Parametric Prediction -- 5. Decomposition of Mixtures -- 6. Response-Based Sampling -- II. Analysis of Treatment Response -- 7. The Selection Problem -- 8. Linear Simultaneous Equations -- 9. Monotone Treatment Response -- 10. The Mixing Problem -- 11. Planning under Ambiguity -- 12. Planning with Sample Data -- III. Predicting Choice Behavior -- 13. Revealed Preference Analysis -- 14. Measuring Expectations -- 15. Studying Human Decision Processes -- References -- Author Index -- Subject Index

Frontmatter -- CONTENTS -- PREFACE -- Introduction -- 1. Clinical Guidelines and Clinical Judgment -- 2. Wishful Extrapolation from Research to Patient Care -- 3. Credible Use of Evidence to Inform Patient Care -- 4. Reasonable Care under Uncertainty -- 5. Reasonable Care with Sample Data -- 6. A Population Health Perspective on Reasonable Care -- 7. Managing Uncertainty in Drug Approval -- Conclusion -- Complement 1A. Overview of Research on Lymph Node Dissection -- Complement 1B. Formalization of Optimal Choice between Surveillance and Aggressive Treatment -- Complement 2A. Odds Ratios and Health Risks -- Complement 3A. The Ecological Inference Problem in Personalized Risk Assessment -- Complement 3B. Bounds on Success Probabilities with No Knowledge of Counterfactual Outcomes -- Complement 4A. Formalization of Reasonable Choice between Surveillance and Aggressive Treatment -- Complement 5A. Treatment Choice as a Statistical Decision Problem -- Complement 6A. Minimax-Regret Allocation of Patients to Two Treatments -- Complement 6B. Derivations for Criteria to Treat X-Pox -- References -- Index

"Manski argues that public policy is based on untrustworthy analysis. Failing to account for uncertainty in an uncertain world, policy analysis routinely misleads policy makers with expressions of certitude. Manski critiques the status quo and offers an innovation to improve both how policy research is conducted and how it is used by policy makers"--Publisher's description.

"Analyses of public policy regularly express certitude about the consequences of alternative policy choices. Yet policy predictions often are fragile, with conclusions resting on critical unsupported assumptions. Then the certitude of policy analysis is not credible. This paper develops a typology of incredible analytical practices and gives illustrative cases. I call these practices conventional certitudes, dueling certitudes, conflating science and advocacy, and wishful extrapolation. I contrast these practices with my vision for credible policy analysis"--National Bureau of Economic Research web site

"Research on collective provision of private goods has focused on distributional considerations. This paper studies a class of problems of decision under uncertainty in which the argument for collective choice emerges from the mathematics of aggregating individual payoffs. Consider decision making when each member of a population has the same objective function, which depends on an unknown state of nature. If agents knew the state of nature, they would make the same decision. However, they may have different beliefs or may use different decision criteria. Hence, they may choose different actions even though they share the same objective. Let the set of feasible actions be convex and the objective function be concave in actions, for all states of nature. Then Jensen's inequality implies that consensus choice of the mean privately-chosen action yields a larger aggregate payoff than does individualistic decision making, in all states of nature. If payoffs are transferable, the aggregate payoff from consensus choice may be allocated to Pareto dominate individualistic decision making, in all states of nature. I develop these ideas. I also use Jensen's inequality to show that a planner with the power to assign actions to the members of the population should not diversify. Finally, I give a version of the collective choice result that holds with consensus choice of the median rather than mean action"--National Bureau of Economic Research web site

This book provides a language and a set of tools for finding bounds on the predictions that social and behavioral scientists can logically make from nonexperimental and experimental data. The economist Charles F. Manski draws on examples from criminology, demography, epidemiology, social psychology, and sociology as well as economics to illustrate this language and to demonstrate the broad usefulness of the tools. There are many traditional ways to present identification problems in econometrics, sociology, and psychometrics. Some of these are primarily statistical in nature, using concepts such as flat likelihood functions and nondistinct parameter estimates. Manski's strategy is to divorce identification from purely statistical concepts and to present the logic of identification analysis in ways that are accessible to a wide audience in the social and behavioral sciences. In each case, problems are motivated by real examples with real policy importance, the mathematics is kept to a minimum, and the deductions on identifiability are derived giving fresh insights. Manski begins with the conceptual problem of extrapolating predictions from one population to some new population or to the future. He then analyzes in depth the fundamental selection problem that arises whenever a scientist tries to predict the effects of treatments on outcomes. He carefully specifies assumptions and develops his nonparametric methods of bounding predictions. Manski shows how these tools should be used to investigate common problems such as predicting the effect of family structure on children's outcomes and the effect of policing on crime rates. Successive chapters deal with topics ranging from the use of experiments to evaluate social programs, to the use of case-control sampling by epidemiologists studying the association of risk factors and disease, to the use of intentions data by demographers seeking to predict future fertility. The book closes by examining two central identification problems in the analysis of social interactions: the classical simultaneity problem of econometrics and the reflection problem faced in analyses of neighborhood and contextual effects

AbstractThis paper presents my thinking and concerns about formation of COVID-19 policy. Policy formation must cope with substantial uncertainties about the nature of the disease, the dynamics of transmission, and behavioral responses. Data uncertainties limit our knowledge of the past trajectory and current state of the pandemic. Data and modeling uncertainties limit our ability to predict the impacts of alternative policies. I explain why current epidemiological and macroeconomic modeling cannot deliver realistically optimal policy. I describe my recent work quantifying basic data uncertainties that make policy analysis difficult. I discuss approaches for policy choice under uncertainty and suggest adaptive policy diversification.