A Simple Distribution-Free Test for Nonnested Model Selection

e-mail: kevin.clarke{at}rochester.edu This paper considers a simple distribution-free test for nonnestedmodel selection. The new test is shown to be asymptoticallymore efficient than the well-known Vuong test when the distributionof individual log-likelihood ratios is highly peaked. MonteCarlo results demonstrate that for many applied research situations,this distribution is indeed highly peaked. The simulation furtherdemonstrates that the proposed test has greater power than theVuong test under these conditions. The substantive applicationaddresses the effect of domestic political institutions on foreignpolicy decision making. Do domestic institutions have effectsbecause they hold political leaders accountable, or do theysimply promote political norms that shape elite bargaining behavior?The results indicate that the latter model has greater explanatorypower. Authors' note: This work was supported by National Science FoundationGrant SES-0213771. I thank Paul K. Huth and Todd L. Allee forgraciously sharing their data and code. I also thank Bear Braumoeller,Curtis Signorino, Tasos Kalandrakis, participants in the NorthEastMethodology Program, New York University, 2003, and the reviewersfor their comments. Errors remain my own. Supplementary materialsare available on the Political Analysis Web site.     

Legitimacy in a Postcolonial Legal System: Public Perception of Procedural Justice and Moral Alignment Toward the Courts in Hong Kong

Legitimacy is said to be comprised of two underlying constructs: obligation to obey and moral alignment. However, legitimacy studies are mainly derived from contexts where the legal system has evolved naturally and is said to reflect the values of society. There is a paucity of research measuring public perceptions of legitimacy in postcolonial settings such as Hong Kong where the legal system was initially transplanted and many of its values may not reflect those of the local population. Procedural justice has been asserted to be a primary antecedent by which legal authorities improve their legitimacy and moral alignment. This study examines whether procedural justice is positively associated with legitimacy and moral alignment with the courts. Moreover, this study tests whether legitimacy is positively associated with cooperation with the courts. Using a random survey of the Hong Kong general population, both questions are answered in the affirmative. Implications are discussed.     

Quasi-experimental designs for community-level public health violence reduction interventions: a case study in the challenges of selecting the counterfactual

Objectives

We highlight the importance of documenting the step-by-step processes used for the selection of comparison areas when evaluating a community-level intervention that targets a large-scale community.

Methods

We demonstrate the proposed method using a propensity score matching framework for an impact analysis of the Cure Violence Public Health Model in Philadelphia. To select comparison communities, propensity score models are run using different levels of aggregation to define the intervention site. We discuss the trade-offs made.

Results

We find wide variation in documentation and explanation in the extant literature of the methods used to select comparison communities. The size of the unit of analysis at which a community is measured complicates the decision processes, and in turn, can affect the validity of the counterfactual.

Conclusions

It is important to carefully consider the unit of analysis for measurement of comparison communities. Assessing the geographic clustering of matched communities to mirror that of the treated community holds conceptual appeal and represents a strategy to consider when evaluating community-level interventions taking place at a large scale. Regardless of the final decisions made in the selection of the counterfactual, the field could benefit from more systematic diagnostic tools that document and guide the steps and decisions along the way, and ask: “could there have been another way of doing each step, and what difference would this have made?” Overall, across community-level evaluations that utilize quasi-experimental designs, documentation of the counterfactual selection process will provide a more fine-grained understanding of causal inference.

     

Non-monetary obstacles to medical care: Evidence from postpartum contraceptives

We use changes to Medicaid immediate postpartum policy to test whether non-monetary costs are meaningful obstacles to health care. Medicaid in several states currently covers long-acting reversible contraceptives (LARCs, including IUDs and implants) immediately following delivery of a child, eliminating much of the time-cost and stress associated with obtaining a LARC. Postpartum LARCs can reduce unintended and short-interval pregnancies, which are associated with adverse neonatal outcomes. Births that occur in Catholic-owned hospitals are an ideal control group, because these hospitals are prohibited from offering family-planning services, including LARCs. Using difference-in-differences and individual-level administrative data from Louisiana and New York, we find eliminating non-monetary obstacles increases take-up of a high-value and highly effective form of contraception. Additionally, we find no evidence of crowd-out of outpatient LARCs.