Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference

Kosuke Imai Department of Politics, Princeton University, Princeton, NJ 08544 e-mail: kimai{at}princeton.edu Gary King Department of Government, Harvard University, 1737 Cambridge Street, Cambridge, MA 02138 Elizabeth A. Stuart Departments of Mental Health and Biostatistics, Johns Hopkins Bloomberg School of Public Health, 624 North Broadway, Room 804, Baltimore, MD 21205 e-mail: estuart{at}jhsph.edu e-mail: king{at}harvard.edu (corresponding author) Although published works rarely include causal estimates frommore than a few model specifications, authors usually choosethe presented estimates from numerous trial runs readers neversee. Given the often large variation in estimates across choicesof control variables, functional forms, and other modeling assumptions,how can researchers ensure that the few estimates presentedare accurate or representative? How do readers know that publicationsare not merely demonstrations that it is possible to find aspecification that fits the author's favorite hypothesis? Andhow do we evaluate or even define statistical properties likeunbiasedness or mean squared error when no unique model or estimatoreven exists? Matching methods, which offer the promise of causalinference with fewer assumptions, constitute one possible wayforward, but crucial results in this fast-growing methodologicalliterature are often grossly misinterpreted. We explain howto avoid these misinterpretations and propose a unified approachthat makes it possible for researchers to preprocess data withmatching (such as with the easy-to-use software we offer) andthen to apply the best parametric techniques they would haveused anyway. This procedure makes parametric models producemore accurate and considerably less model-dependent causal inferences. Authors' note: Our thanks to Dan Carpenter and Jeff Koch fordata; Alberto Abadie, Neal Beck, Sam Cook, Alexis Diamond, BenHansen, Guido Imbens, Olivia Lau, Gabe Lenz, Paul Rosenbaum,Don Rubin, and Jas Sekhon for many helpful comments; and theNational Institutes of Aging (P01 AG17625-01), the NationalInstitute of Mental Health (MH066247), the National ScienceFoundation (SES-0318275, IIS-9874747, SES-0550873), and thePrinceton University Committee on Research in the Humanitiesand Social Sciences for research support. Software to implementthe methods in this paper is available at http://GKing.Harvard.edu/matchitand a replication data file is available as Ho et al. (2006).     

Detection of nitro-organic and peroxide explosives in latent fingermarks by DART- and SALDI-TOF-mass spectrometry

The ability of two mass spectrometric methods, surface-assisted laser desorption/ionization-time of flight-mass spectrometry (SALDI-TOF-MS) and direct analysis in real time (DART-MS), to detect the presence of seven common explosives (six nitro-organic- and one peroxide-type) in spiked latent fingermarks has been examined. It was found that each explosive could be detected with nanogram sensitivity for marks resulting from direct finger contact with a glass probe by DART-MS or onto stainless steel target plates using SALDI-TOF-MS for marks pre-dusted with one type of commercial black magnetic powder. These explosives also could be detected in latent marks lifted from six common surfaces (paper, plastic bag, metal drinks can, wood laminate, adhesive tape and white ceramic tile) whereas no explosive could be detected in equivalent pre-dusted marks on the surface of a commercial lifting tape by the DART-MS method due to high background interference from the tape material. The presence of TNT and Tetryl could be detected in pre-dusted latent fingermarks on a commercial lifting tape for up to 29 days sealed and stored under ambient conditions.     

The role of empathy in anger arousal in violent offenders and university students

A lack of empathic responsiveness toward others has been consistently identified as an important antecedent to aggressive behavior and violent crime, with many rehabilitation programs for violent offenders incorporating treatment modules that are specifically designed to increase offender empathy. This study examined the extent to which cognitive (perspective taking) and affective (empathic concern, personal distress) empathy predicted anger in a clinical (male prisoners convicted of a violent offense) and a nonclinical (student) sample. Perspective taking emerged as the strongest predictor of self-reported anger in response to an interpersonal provocation, as well as being most consistently related to scores on measures of general trait anger and methods of anger control. While the relationship between perspective taking and anger was apparent for offenders as well as students, the results did not support the idea that an inability to perspective take is a particular characteristic of violent offenders.     

Social Motives Underlying Antisocial Behavior Across Middle School Grades

The goal of the study was to examine whether social motives (social mimicry, mutual attraction, and unreciprocated attraction) predict changes in antisocial behavior across middle school grades. The 2,003 initial participants (55% girls) were drawn from a larger longitudinal study of urban public school students: 44% Latino, 26% African-American, 10% Asian, 9% Caucasian, and 11% multiracial. Analyses of peer nominations and teacher-rated behavior included five waves of data between the fall of sixth grade and the spring of eighth grade (n = 1,260–1,347 for longitudinal analyses). Supporting the social mimicry hypothesis, students who associated peer-directed aggression with high social status in the beginning of middle school engaged in elevated levels of antisocial conduct during the second year in the new school. Additionally, unreciprocated attraction toward peers who bully others in the beginning of middle school was related to increased antisocial behavior in the last year of middle school. No support was obtained for the mutual attraction hypothesis. The findings provide insights about possible social motives underlying susceptibility to negative peer influence.

Is it really just a game? Copyright and online role-playing games

Legal context. Massively multiplayer online role-playing games(MMORPGs) are a craze that has swept the globe. Online gamershave been reported to spend 22 hours per week online playingtheir favourite games while there have been reports of playersspending up to 55 hours at a time playing. Not all gamers arehobby gamers, nor are they just teenagers having fun. A markethas grown around MMORPGs and a lucrative online market has emergedoutside the games for the sale of game characters and items.The value of this market has been estimated at US$880 million.At the heart of disputes concerning the sale of game charactersand items is the question of copyright ownership. Game providersclaim that the End User Licence Agreements (EULAs) give themintellectual property ownership and rights over any dealingswith the game characters and items. Many gamers on the otherhand are abhorrent at the assertion that they have no claimto characters and items that they have spent many hours developing. Key points. The first issue that needs to be considered is whethercopyright subsists at all in the game characters and items.The next question to be considered is who owns the copyrightin in-game characters and items. To answer the question, onemust look to the EULAs, but the EULAs do not provide all theanswers because issues such as moral rights cannot be governedby EULAs. Further, the practice of farming by companies runningdigital sweatshops complicates the relationship between gamersand game providers. Practical significance. There have been numerous disputes concerningthe game characters and items between game developers, gamers,and farming companies. This article examines the key copyrightissues at stake.     

Ethnicity, gender, and global risk indicators in the lives of status offenders coming to the attention of the juvenile court

The present study examined the risks and needs of status offenders in comparison to an at-large juvenile court sample, with specific attention paid to factors related to gender and ethnicity. Status offenders displayed significantly higher risk scores than the comparison sample in domains associated with both family and parenting concerns and educational concerns. In addition, females displayed higher risk levels than males and White youth displayed significantly higher risk levels than minority youth across a wide variety of risk domains. Further analyses were conducted regarding the participation of African American males and females in a program designed as an alternative to detention. For both groups, successful program completion was accompanied by little or no further court involvement, whereas failure to complete the program was related to a variety of negative outcomes. However, African American females and males successfully completing program requirements displayed different risks and needs at the outset of their participation.     

Have Cities Shifted to Outcome‐Oriented Performance Reporting?—A Content Analysis of City Budgets

“Outcome” orientation has been emphasized in performance measurement and reporting in recent years. Using budgetary documents of the largest cities in the United States, this paper analyzes more than 4,800 performance measures reported by 21 cities to show that clear progress toward outcome‐oriented performance measurement has been made. It also shows that the selection of performance measures differs among types of municipal services and is driven partly by professionalism in city management and the influence of professional organizations. The paper concludes by discussing the implications of the findings and potential future improvements of performance reporting.     

论故意在德日刑法中地位的变化

故意在德、日刑法的犯罪论体系中的地位经历了一个变化的过程,即由从以往的有责性中分离到构成要件该当性中,这种变化一方面是由于司法实践中实务操作的需要,另一方面也说明了犯罪的主观方面在犯罪论体系中所起到的重要作用,同时说明了刑法对行为人罪过的重视。这在某一方面也说明了人类社会是某一观念的共同体。