Using Auxiliary Data to Estimate Selection Bias Models, with an Application to Interest Group Use of the Direct Initiative Process

Recent work in survey research has made progress in estimatingmodels involving selection bias in a particularly difficultcircumstance—all nonrespondents are unit nonresponders,meaning that no data are available for them. These models arereasonably successful in circumstances where the dependent variableof interest is continuous, but they are less practical empiricallywhen it is latent and only discrete outcomes or choices areobserved. I develop a method in this article to estimate thesemodels that is much more practical in terms of estimation. Themodel uses a small amount of auxiliary information to estimatethe selection equation parameters, which are then held fixedwhile estimating the equation of interest parameters in a maximum-likelihoodsetting. After presenting Monte Carlo analyses to support themodel, I apply the technique to a substantive problem: Whichinterest groups are likely to to be involved in support of potentialinitiatives to achieve their policy goals?     

Using Experiments to Estimate the Effects of Education on Voter Turnout

The powerful relationship between education and voter turnout is arguably the most well-documented and robust finding in American survey research. Yet the causal interpretation of this relationship remains controversial, with many authors suggesting that the apparent link between education and turnout is spurious. In contrast to previous work, which has relied on observational data to assess the effect of education on voter turnout, this article analyzes two randomized experiments and one quasi-experiment in which educational attainment was altered exogenously. We track the children in these experiments over the long term, examining their voting rates as adults. In all three studies, we find that exogenously induced changes in high school graduation rates have powerful effects on voter turnout rates. These results imply that the correlation between education and turnout is indeed causal. We discuss some of the pathways by which education may transmit its influence.     

A Propensity Score Reweighting Approach to Estimating the Partisan Effects of Full Turnout in American Presidential Elections

John DiNardo 440 Lorch Hall, Ford School of Public Policy, University of Michigan, Ann Arbor, MI 48109-1220 e-mail: jdinardo{at}umich.edu Borrowing an approach from the literature on the economics ofdiscrimination, we estimate the impact of nonvoters on the outcomeof presidential elections from 1952–2000 using data fromthe National Election Study (NES). Our estimates indicate thatnonvoters are, on average, slightly more likely to support theDemocratic Party. Of the 13 presidential elections between 1952and 2000 we find no change in the eventual outcome of the electionwith two possible exceptions: 1980 and 2000. Thus our resultsare not all that dissimilar from other research on participation.Higher turnout in the form of compulsory voting would not radicallychange the partisan distribution of the vote. When electionsare sufficiently close, however, a two percentage point increasemay suffice to affect the outcome. Limitations of the NES datawe use suggest that our estimates underestimate the impact ofnonparticipation. We also compare our method with other econometrictechniques. Finally, using our findings we speculate as to whythe Democratic Party fails to undertake widespread "get outthe vote" or registration drives.     

Using Qualitative Information to Improve Causal Inference

Using the Rosenbaum (2002, 2009) approach to observational studies, we show how qualitative information can be incorporated into quantitative analyses to improve causal inference in three ways. First, by including qualitative information on outcomes within matched sets, we can ameliorate the consequences of the difficulty of measuring those outcomes, sometimes reducing p‐values. Second, additional information across matched sets enables the construction of qualitative confidence intervals on effect size. Third, qualitative information on unmeasured confounders within matched sets reduces the conservativeness of Rosenbaum‐style sensitivity analysis. This approach accommodates small to medium sample sizes in a nonparametric framework, and therefore it may be particularly useful for analyses of the effects of policies or institutions in a small number of units. We illustrate these methods by examining the effect of using plurality rules in transitional presidential elections on opposition harassment in 1990s sub‐Saharan Africa.     

A Framework for Analyzing Emergency Management with an Application to Federal Budgeting

Emergency management is a complex policy subsystem that involves an intergovernmental, multiphased effort to mitigate, prepare for, respond to, and recover from disasters. This article develops a framework for analyzing the fiscal and functional aspects of disaster policy. It uses established theories of intergovernmental relations to offer a rationale for examining the capabilities required to implement disaster policy and the behavioral incentives that drive policy formulation. In particular, the article identifies the extent to which the capabilities and political objectives characteristic of each level of government are aligned, and illustrates the interplay between incentives and competencies by reviewing the federal disaster funding process. The current rules for federal budgeting may inappropriately promote spending on disaster response and recovery, while de-emphasizing mitigation and preparedness. Various proposals for reform could establish more coherent incentives, making disaster spending more consistent with the relative functional capabilities of the various levels of government.     

Measuring Disparity in Government Procurement: Problems with Using Census Data in Estimating Availability

The Supreme Court's ruling in City of Richmond v. J.A. Croson (1989) has restricted the use of government procurement assistance programs for minorities and women without the prerequisite support of a disparity study. Recently, an increasing number of disparity studies have been rejected by the courts as "junk science" and the related programs have been ruled unconstitutional. A central issue in these cases has been the approach used to estimate the availability of minority and women firms. Data from the Economic Census are commonly used as the basis for these availability estimates. However, there are significant problems and limitations with the Census data relative to the Croson guideline that the availability of women and minority firms should reflect the number of qualified, willing, and able firms. Given the number and difficulty of the required adjustments to the Census data, it is unlikely that these data will provide availability estimates that are accurate enough to allow for valid statistical tests of an inference of discriminatory exclusion. If minimizing court challenges is a goal of the public administrator who is responsible for the program, then the recommendation here is that a primary source of availability data should be considered. Furthermore, the information system needed to support the women and minority assistance programs should be designed and installed prior to initiating the program.     

Using Geographic Information Systems to Measure District Change, 2000-2002

In this article, I use geographic information systems to developa continuous measure of district continuity and change followingthe 2000–02 congressional redistricting cycle. The newmeasure provides details of where the new population in a districtcame from and how the old population was distributed withinnew districts. This measure is then used to demonstrate theindependent and interactive influence of district change oncompetition for congressional elections.     

Estimating the potential impact of nonvoters on outcomes of parliamentary elections in proportional systems with an application to German national elections from 1949 to 2009

“If turnout was 100%, would it affect the election result?” is a frequently asked research question. So far, the question has been primarily answered regarding the changes in the distribution of votes. This article extends the analysis to changes in the distribution of seats and government formation. It therefore proposes a method that factors in apportionment methods, election threshold, sizes of parliaments, leverage of nonvoters, closeness of election results, and individual characteristics of nonvoters. The method is then applied to German national elections from 1949 to 2009. The application shows that Germany's Social Democratic Party (SPD) would have gained from the counterfactual participation of nonvoters, although usually not enough to result in a government change. However, the elections of 1994 and 2005 show evidence that such a change could have happened.     

Designing and Analyzing Randomized Experiments: Application to a Japanese Election Survey Experiment

Randomized experiments are becoming increasingly common in political science. Despite their well-known advantages over observational studies, randomized experiments are not free from complications. In particular, researchers often cannot force subjects to comply with treatment assignment and to provide the requested information. Furthermore, simple randomization of treatments remains the most commonly used method in the discipline even though more efficient procedures are available. Building on the recent statistical literature, we address these methodological issues by offering general recommendations for designing and analyzing randomized experiments to improve the validity and efficiency of causal inference. We also develop a new statistical methodology to explore causal heterogeneity. The proposed methods are applied to a survey experiment conducted during Japan's 2004 Upper House election, where randomly selected voters were encouraged to obtain policy information from political parties' websites. An R package is publicly available for implementing various methods useful for designing and analyzing randomized experiments .     

网络监督：打破信息不对称的有效途径

信息不对称是导致腐败现象产生的一个重要根源,在我国主要表现为：官员与民众信息的不对称、腐败者所在组织内部和外部的信息不对称、底层与上层的信息不对称及腐败者与监督者的信息不对称。网络监督是新时代产生的新型舆论监督方式,具有监督主体广泛、信息全面、方便快捷、运作高效等特点,能有效地打破监督主客体间的信息不对称,促进反腐倡廉建设。同时,对于网络监督过程中存在的非理性、权责不平衡和监督群体有限性等缺陷,要有清醒的认识,应逐步加以解决与改进。     

Turning Point Analysis: Using Survey Research to Call Changes in Consumer Behavior and Predict Sales Taxes

Forecasters often disagree on revenue predictions because of differing techniques. Some states, such as Utah, have turned to the use of survey research methods to avoid this dilemma. This article reviews many of the national forecasting models examining consumer sentiment currently in use. And it compares the Utah experience with surveys used in other states.     

Using the State for Change: Towards an Effective Labour Government

The capacity of the state to deliver transformative social and economic change appears more limited today than since Labour was last in government. A future Labour government will therefore need to reckon with the challenges this presents when it comes to harnessing the power of the state to distribute power, wealth, and opportunity, effectively. This article considers two aspects of state power. The first is the ability of the state to enforce laws, and in doing so shape social and economic norms. With reference to past successes and failures, there is discussion of how laws and regulations could be made more effective. The second aspect is state intervention in the economy, and the circumstances in which it is possible and desirable to nationalise key industries. The case is made for a thorough assessment of the efficiency and efficacy of such interventions in the economy, especially when weighed against other policy priorities.     

Comparing Group and Subgroup Cohesion Scores: A Nonparametric Method with an Application to Brazil

This article builds a nonparametric method for inference fromroll-call cohesion scores. Cohesion scores have been a stapleof legislative studies since the publication of Rice's 1924thesis. Unfortunately, little effort has been dedicated to understandingtheir statistical properties or relating them to existing modelsof legislative behavior. I show how a common use of cohesionscores, testing for distinct voting blocs, is severely biasedtoward Type I error, practically guaranteeing significant findingseven when the null hypothesis is correct. I offer a nonparametricmethod—permutation analysis—that solves the biasproblem and provides for simple and intuitive inference. I demonstratewith an examination of roll-call voting data from the BrazilianNational Congress.     

The Synthetic Control Method for Comparative Case Studies: An Application Estimating the Effect of Managerial Discretion Under Performance Management

Public management researchers are often interested in estimating the effects of aggregate-level management reforms and policy changes, but they frequently rely on observational data that pose a number of threats to internal validity. The synthetic control method for comparative case studies (SCM) has great potential for advancing public management scholarship by addressing some of the methodological challenges associated with observational data and providing intuitive graphical results that help researchers communicate their findings to audiences unfamiliar with quantitative methods. SCM uses a transparent, data-driven algorithm for selecting a weighted combination of control units that act as a plausible counterfactual for estimating causal effects. This article demonstrates SCM by investigating the effect of enhancing managerial discretion under performance accountability systems in the context of public education. The article also provides a number of possible avenues for future public management research using SCM and practical guidance for applying the method.     

Joining-Up Government in the UK: Towards Public Services for an Information Age

The reform of public services has preoccupied managers for several decades. Nevertheless, it is my contention that the present reform agenda has some plausible claims to be different from much that went before. The vision that has come to the fore in the Australian federal government's Clients First Program (Information Technology Review Group 1995), in the Clinton/Gore administration's Access America report (Government IT Services 1997) andthe recent British White Paper, Modernising Government (Cabinet Office 1999) not only promotes the 'client orientation' in public administration, but also reflects a belief in the crucial contribution to be made by information and communication technologies (ICTs). This is a vision for an information age (POST 1998). It is being driven by the conviction that public management has too often been modelled on business 'as it was in the age of US Steel, not the age of Microsoft, Apple, Wal-Mart and Federal Express' (Gore 1993:xiii).     

运用网络技术 推进信息公开

高桥石化作为中国石化系统的骨干生产企业、上海市重要能源生产基地,近年来公司积极推进信息公开工作,秉持“制度＋科技”的理念,充分运用网络技术,不断推进重点领域、关键环节的信息公开,通过不断健全事前、事中、事后全程网上监察体系,规范权力运行、提升管理效率,源头预防腐败,促进各级管理人员不断提高决策能力和领导水平。     

A Pragmatic Approach to Designing Changes Using Convergent Interviews: Occupational Violence Against Paramedics as an Illustration

Developing a change program to address complex problems can appear overwhelming. This study presents how an inductive diagnostic technique known as convergent interviewing can provide a summary of the critical issues that could be addressed by a change program. A systems perspective is used to show how the issues raised by the diagnostic process can be targeted in order to have the most effect and be pragmatically implementable. The use of the tool is illustrated by analysing an employee problem that needs to be addressed in public services, the high rates of occupational violence against paramedics. The resulting inductive systems model can be used for diagnosis or for informing a variety of change interventions. Convergent interviews are relatively easy to use, powerful, and applicable to many situations. This tool is particularly useful for developing innovations regarding a specific problem, changes that could be a source of substantial public value.