Recently Published Books

Summer 2003, Volume 25, Number 1

Partial Identification of Probability Distributions
By Charles F. Manski
Springer, 2003, 178 pages

Sample data alone never suffice to draw conclusions about populations. Inference always requires assumptions about the population and sampling process. Statistical theory has revealed much about how the strength of assumptions affects the precision of point estimates, but it has had much less to say about how it affects the identification of population parameters. Indeed, it has been commonplace to think of identification as a binary event—a parameter is either identified or not—and to view point identification as a precondition for inference. Yet there is enormous scope for fruitful inference using data and assumptions that partially identify population parameters. This book explains why and shows how.

In a rigorous and thorough manner, the book presents the main elements of Charles Manski’s research on partial identification of probability distributions. One focus is prediction with missing outcome or covariate data. Another is decomposition of finite mixtures, with application to the analysis of contaminated sampling and ecological inference. A third major focus is the analysis of treatment response. Whatever the particular subject under study, the presentation follows a common path. The author first specifies the sampling process generating the available data and asks what may be learned about population parameters using the empirical evidence alone. He then asks how the (typically) setvalued identification regions for these parameters shrink if various assumptions are imposed. The approach to inference that runs throughout the book is deliberately conservative and thoroughly nonparametric.

The chapters are “Missing Outcomes”; “Instrumental Variables”; “Conditional Prediction with Missing Data”; “Contaminated Outcomes”; “Regressions, Short and Long”; “Response-Based Sampling”; “Analysis of Treatment Response”; “Monotone Treatment Response”; “Monotone Instrumental Variables”; and “The Mixing Problem.”

Navigating Public Opinion: Polls, Policy, and the Future of American Democracy
Edited by Jeff Manza, Fay Lomax Cook, and Benjamin Page
Oxford University Press, 2002, 392 pages

Do politicians listen to the public? How often and when? Or are the views of the public manipulated or used strategically by political and economic elites? “Navigating Public Opinion” brings together leading scholars of American politics to assess and debate these questions. It describes how the relationship between opinion and policy has changed over time; how key political actors use public opinion to formulate domestic and foreign policy; and how new measurement techniques might improve our understanding of public opinion in contemporary polling and survey research.

The distinguished contributors shed new light on several long-standing controversies over policy responsiveness to public opinion. Featuring a new analysis by Robert Erikson, Michael MacKuen, and James Stimson that builds from their path-breaking work on how public mood moves policy in a macro-model of policymaking, the volume also includes several critiques of this model by Lawrence Jacobs and Robert Shapiro, another critique by G. William Domhoff, and a rejoinder by Erikson and his coauthors.

Other highlights include discussions of how political elites, including state-level policymakers, presidents, and makers of foreign policy, use—or shape—public opinion; and analyses of new methods for measuring public opinion such as survey-based experiments, probabilistic polling methods, non-survey-based measures of public opinion, and the potential and limitations of Internet polls and surveys. Introductory and concluding essays provide useful background context and offer an authoritative summary of what is known about how public opinion influences public policy.

Noted Henry Brady, a professor at the University of California at Berkeley, “The dynamic interplay of public opinion and political power takes center stage as an all-star cast of academics shows how public opinion shapes and directs public policy in the U.S. The impact of public mood on welfare, foreign policy, social security, and labor policy is tracked, explained, and evaluated to answer the question: ‘When the people speak, do politicians listen?’”

Community Policing: Can It Work?
Edited by Wesley G. Skogan
Wadsworth, available June 2003, 272 pages

This book is the long-awaited culmination of the most extensive study of community policing’s efficacy and was funded by the Searle Family Fund. The chapters cover all aspects of community policing, from management to implementation and public perception. The various contributors debate the question “Can community policing work?” with an impressive array of surveys, case studies, field observations, and statistical data—and often arrive at conflicting conclusions. Contributors include Jeremy Travis, Jack R. Greene, John E. Eck, Stephen D. Mastrofski, Dennis P. Rosenbaum, and Jeffrey A. Roth, among others.

In following how various experts address the question, readers are also gaining important insights into the direction that future research will take on this issue.

The first two chapters, “Trends in the Adoption of Community Policing,” and “Community Policing and Organization Change,” address evidence of the extent to which community policing has actually been adopted around the United States. In the following chapter, “Representing the Community in Community Policing” is explored. Another section also deals with community policing from the perspective of the police officers, examining the impact of community policing on their work and whether these officers are “buying” into it.

The latter part of the book, “Community Policing and Problem Solving” and “Why Don’t Problems Get Solved?” reviews the many obstacles to solving a community’s problems.

The final chapter, “Community Policing and the Quality of Neighborhood Life,” concludes that community policing can work.