Logistic Regression in Rare Events Data

We study rare events data, binary dependent variables with dozensto thousands of times fewer ones (events, such as wars, vetoes,cases of political activism, or epidemiological infections)than zeros ("nonevents"). In many literatures, these variableshave proven difficult to explain and predict, a problem thatseems to have at least two sources. First, popular statisticalprocedures, such as logistic regression, can sharply underestimatethe probability of rare events. We recommend corrections thatoutperform existing methods and change the estimates of absoluteand relative risks by as much as some estimated effects reportedin the literature. Second, commonly used data collection strategiesare grossly inefficient for rare events data. The fear of collectingdata with too few events has led to data collections with hugenumbers of observations but relatively few, and poorly measured,explanatory variables, such as in international conflict datawith more than a quarter-million dyads, only a few of whichare at war. As it turns out, more efficient sampling designsexist for making valid inferences, such as sampling all availableevents (e.g., wars) and a tiny fraction of nonevents (peace).This enables scholars to save as much as 99% of their (nonfixed)data collection costs or to collect much more meaningful explanatoryvariables. We provide methods that link these two results, enablingboth types of corrections to work simultaneously, and softwarethat implements the methods developed.     

Age and the Explanation of Crime, Revisited

Age is one of the most robust correlates of criminal behavior. Yet, explanations for this relationship are varied and conflicting. Developmental theories point to a multitude of sociological, psychological, and biological changes that occur during adolescence and adulthood. One prominent criminological perspective outlined by Gottfredson and Hirschi claims that age has a direct effect on crime, inexplicable from sociological and psychological variables. Despite the attention this claim has received, few direct empirical tests of it have been conducted. We use data from Pathways to Desistance, a longitudinal study of over 1,300 serious youthful offenders (85.8 % male, 40.1 % African-American, 34.3 % Hispanic, 21.0 % White), to test this claim. On average, youths were 16.5 years old at the initial interview and were followed for 7 years. We use multilevel longitudinal models to assess the extent to which the direct effects of age are reduced to statistical and substantive non-significance when constructs from a wide range of developmental and criminological theories are controlled. Unlike previous studies, we are able to control for changes across numerous realms emphasized within differing theoretical perspectives including social control (e.g., employment and marriage), procedural justice (e.g., perceptions of the legitimacy and fairness of the legal system), learning (e.g., gang membership and exposure to antisocial peers), strain (e.g., victimization and relationship breakup), psychosocial maturity (e.g., impulse control, self-regulation and moral disengagement), and rational choice (e.g., costs and rewards of crime). Assessed separately, these perspectives explain anywhere from 3 % (procedural justice) to 49 % (social learning) of the age-crime relationship. Together, changes in these constructs explain 69 % of the drop in crime from ages 15 to 25. We conclude that the relationship between age and crime in adolescence and early adulthood is largely explainable, though not entirely, attributable to multiple co-occurring developmental changes.     

Infighting and Ideology: How Conflict Informs the Local Culture of the Chicago Dyke March

Although the study of local cultures has become established in American sociology, it often ignores the contested nature of how culture emerges and is negotiated within the context of small groups. To this end, we address the concept of infighting, a subtype of conflict, as it operates within a small group framework. Building on an ethnographic study of the Chicago Dyke March, we demonstrate that infighting highlights competing ideologies that may remain implicit in the absence of such conflict. Infighting treats divergent meaning systems as part of local contention between rival cliques and power centers. These ideological battles both reflect pre-existing differences between subgroups and serve to make explicit and public such differences, both in their background characteristics and in their interests. In the process infighting directs attention away from shared concerns and group building to questions of strategy, transforming the small group into an arena of ideological production and factional rivalry. Infighting recasts a group from a space of consensus to a contested political arena. We elaborate four analytic processes through which infighting connects to ideology and small group culture: infighting emphasizes the multivocality of meaning, cultural heterogeneity, an equilibrium of inclusion and group boundaries, and planning in light of ideologies of power.     

The impact of police charges in incidents of wife abuse

The present study addressed the impact of an urban police force laying criminal charges in cases of wife abuse. Follow-up data from battered women and from police officers were collected to identify the long-term consequences of this police policy that began in 1981, including any negative or unintended side effects. Results indicated that the policy resulted in a dramatic increase in police-laid charges (2500%), and a shift from the Family to the Criminal Division of Provincial Court. Based on interview data, victims did not decrease their requests for police service (a feared side effect) and reported a significantly higher level of satisfaction with police service in this area. A significant reduction in police calls and victim-reported violence was associated with police intervention, especially when charges were laid. Paradoxically, police officers' attitudes about the policy were more negative than the actual positive changes that they helped to produce. Considerations for future research and professional training are outlined.