Comparing Experimental and Matching Methods Using a Large-Scale Voter Mobilization Experiment

Alan S. Gerber and Donald P. Green Yale University, Institution for Social and Policy Studies, P.O. Box 208209, 77 Prospect Street, New Haven, CT 06520 e-mail: kevin.arceneaux{at}temple.edu (corresponding author) e-mail: alan.gerber{at}yale.edu e-mail: donald.green{at}yale.edu In the social sciences, randomized experimentation is the optimalresearch design for establishing causation. However, for a numberof practical reasons, researchers are sometimes unable to conductexperiments and must rely on observational data. In an effortto develop estimators that can approximate experimental resultsusing observational data, scholars have given increasing attentionto matching. In this article, we test the performance of matchingby gauging the success with which matching approximates experimentalresults. The voter mobilization experiment presented here comprisesa large number of observations (60,000 randomly assigned tothe treatment group and nearly two million assigned to the controlgroup) and a rich set of covariates. This study is analyzedin two ways. The first method, instrumental variables estimation,takes advantage of random assignment in order to produce consistentestimates. The second method, matching estimation, ignores randomassignment and analyzes the data as though they were nonexperimental.Matching is found to produce biased results in this applicationbecause even a rich set of covariates is insufficient to controlfor preexisting differences between the treatment and controlgroup. Matching, in fact, produces estimates that are no moreaccurate than those generated by ordinary least squares regression.The experimental findings show that brief paid get-out-the-votephone calls do not increase turnout, while matching and regressionshow a large and significant effect.     

Dancing To Whose Tune? Change And Investigations In Hm Customs And Excise

The public sector has been subject to significant organizational and cultural change in the past two decades. The purpose of change has been the cost-efficient and cost-effective delivery of public services and functions. The process of change has been concerned with the best means to do this, whether in structural, cultural and procedural terms. Without careful determination of the services and functions from the onset, the process, however, can become an end in itself, reflecting the comments of the Head of the Civil Service when he said that he did not know the final shape of the civil service on the grounds that ‘it is not unusual . . . for an organisation in the process of evolution not to know what its final state will be’ (Dynes and Walker 1995, p. 99). Where an organization has assumed its core functions are clearly defined and understood but where they are not explicitly used to provide the purpose to shape and direct the process of change, that process may be influenced more by generic external imperatives on structural, cultural and managerial reform that developed from the 1988 Next Steps report than by the organization’s core functions. The article questions assumptions that, by itself, an emphasis on the former will facilitate the performance of the latter. It suggests that the process of challenging culture and structure may have adverse consequences until the purpose of change and the functions of the organization are used to shape and inform the process. It looks at the impact of the process of change on a core organizational function in one large government department that has undergone significant change – major investigations within HM Customs and Excise. It considers that change may be, to use the idiom of earlier research into change and the department, partly about teaching organizations to dance the Next Steps, and partly about ensuring that they keep dancing, but it is also about teaching departments that dancing is best done to tunes that inform the steps.     

Alternatives to Custody for High-Risk Young Offenders: The Multisystemic Therapy Approach

This article describes the implementation of randomised trials in Ontario, Canada, of a community-based, therapeutic intervention for youths who would be candidates for custodial sentences because of the severity or persistence of their criminal behaviour. Many recognise the need to reduce custody stays but the realisation of that goal requires the creation of community-based programs which judges believe will not put the public at risk. Reviews of the empirical literature indicated that Multisystemic Therapy could be a cost-effective, individualised, community-based alternative to custody that reduces long and short-term recidivism of high-risk youths.     

Oregon: does physician-assisted suicide work?

Since November 1997, Oregon, a State in the United States of approximately 3.3 million people, has allowed physician-assisted suicide, although not euthanasia, by virtue of the Death with Dignity Act. Before the Act, physician-assisted suicide, as in Australia and other common law jurisdictions, was illegal. Under the Act, the Oregon Department of Human Services is required to collect information and provide an annual report. The Sixth Annual Report on Oregon's Death with Dignity Act was released on 10 March 2004.     

Gardner; Re BWV: resolved and unresolved issues at end of life

The Medical Treatment Act 1988 (Vic) gives statutory recognition to a patient's (or their agent or guardian if incompetent) right to refuse medical treatment. The case of Gardner; Re BWV confirmed that medical treatment as defined under the Act included artificial nutrition and hydration and as such could be withdrawn, notwithstanding that this would result in the patient's death. This article analyses Gardner; Re BWV and argues that, by deliberately dealing narrowly with the issues at hand, both the Victorian Civil and Administrative Tribunal at first instance and the Victorian Supreme Court knowingly left BWV to die from dehydration over a period of weeks. By not addressing these issues, the tribunal, and more particularly the Supreme Court, lost an opportunity for a reform of the law, so urgently needed at end of life, which would have allowed for "mercy killing", thus sparing BWV and her family the lingering death she was given.     

Deciphering indented impressions on plastic

The questioned document laboratory is often called upon to decipher writing that has been erased, obliterated, or that has faded. In cases like these, the original writing is no longer legible to the naked eye, but may be enhanced using various light sources. Certain remnants of the ink's components absorb into the substrate's fibers and can be visualized, usually as luminescence or absorbance. A case is described here that involved the theft of a credit card. An empty plastic credit card holder was found in the possession of a suspect, and as submitted for examination. Indented impressions could be discerned on its clear plastic window and presumably originated from the credit card that had been held in the envelope. These indented impressions were deciphered in the hope that they would reveal enough details from the credit card to establish a connection between the plastic envelope and the stolen credit card. With methods generally utilized in the toolmarks and materials laboratory and the photography laboratory of the Israel Police, most of the indented impressions on the plastic were deciphered and a connection between the plastic envelope and the stolen credit card was demonstrated.     

Characterization of condom lubricant components using Raman spectroscopy and Raman chemical imaging

A condom can be described as a protective sheath used as a contraceptive or to protect against sexually transmitted diseases. However, individuals also use condoms during the commission of sexual assaults to prevent identification through deposited biological material. Raman spectroscopy offers a novel approach to identifying the presence of condom lubricant components. Furthermore, Raman chemical imaging expands on conventional Raman spectroscopy to characterize multiple condom lubricant components simultaneously in a manner that effectively demonstrates heterogeneous sample mixtures both spectrally and spatially. Known reference materials, liquid and solid lubricant components of common condom brands were successfully characterized using Raman dispersive spectroscopy and Raman chemical imaging without extensive sample preparation inherent to other analytical methods. The characterization of these materials demonstrates the potential of this technique to become a routine screening method for condom lubricants. This preliminary investigation provides a basis for future studies to determine the feasibility of Raman spectroscopy and Raman chemical imaging for condom lubricant trace detection in case type samples.     

Mandating insurance offers for low-wage workers: an evaluation of labor market effects

Employing a simultaneous model of part-time status, health insurance offers, and wages, we examine the impacts on employment and health insurance coverage of nondiscrimination rules in the tax code governing employer-sponsored health insurance. Using 1988 and 1993 Employee Benefits Supplements to the Current Population Surveys and variations in health insurance premiums and minimum wages, we find that health insurance coverage among low-wage primary earners is increased by at most 31 percent by the policy, at a cost of an estimated 0.8-5.4-percentage-point decrease in full-time employment for low-wage workers.