Social Policy, Feminism, and Research on Violence in Close Relationships

The history of research on intimate partner violence is reviewed, with a special focus on how my own work in this area has evolved. The role of researcher values in the research process is highlighted. Some of the issues emerging from this review are the need for better measures of intimate partner violence, reasons why women's violence has been ignored by many researchers, and a discussion of the conditions under which women display violence. Policy implications of this research are discussed .     

Solutions for a class of invex programming problems

A nonconvex constrained optimization problem is considered in which the constraints are of the form of generalized polynomials. An invexity kernel is established for this class of problem, and a consequent theorem gives sufficient conditions for the solutions of such problems.     

Consensus By Identifying Extremists

Given a finite state space and common priors, common knowledge of the identity of an agent with the minimal (or maximal) expectation of a random variable implies consensus, i.e., common knowledge of common expectations. This extremist statistic induces consensus when repeatedly announced, and yet, with n agents, requires at most log₂ n bits to broadcast.     

Effects of community violence exposure and parental mental health on the internalizing problems of urban adolescents

Previous research has documented an association between adolescent community violence exposure (CVE) and poor psychological functioning. The purpose of this study is to delineate the relations of CVE, parental mental health, and adolescent PTSD and depression. Participants consisted of 121 pairs of junior high and high school students and their parents. Adolescents completed measures to assess their history of violence exposure and current psychological functioning. Parents completed a demographic questionnaire and measures assessing their psychological functioning. Hierarchical regression analyses were conducted, and results indicated that, after controlling for demographic variables and family violence exposure, parental mental health emerged as a moderating variable in the relation between CVE and adolescent-rated PTSD, but not in the association between adolescent CVE and depression. Clinical implications of this study and directions for future research are discussed.     

Subcommunity Change in a Changing Metropolis*

Residential areas in cities and suburbs change as they age. The conventional concepts that represent this process are succession and the neighborhood life cycle. In this study we use cohort analysis and multiple regression on small-area data from four censuses to examine population growth patterns among subcommunities in metropolitan Chicago,1940–70. The major findings: among city and suburban areas, cohort is a strong predictor of growth and loss. All suburbs grew early in the period studied, but older suburbs stabilized in the 1960s. Among city areas and suburbs, familism is a strong predictor of growth. Many areas in the city began to lose population in the 1950s, with accelerated loss in the following decade. City areas undergoing racial change in the 1950s lost population rapidly in the following decade. We conclude that the succession model, which is embedded in Burgess' city growth model, no longer accounts for change at the subcommunity level. Thus, the research confirms the life-cycle model but also points to the need for a new macro model of a nongrowing metropolis.     

Turning points in the romantic history of emerging adults

This study examined patterns of romantic relationship turning points in 100 Israeli emerging adults (54 males) who were followed from age 22 to 29. Analyses of interviews at age 29 yielded four distinctive patterns of romantic transitions that are associated with different levels of concurrent well-being: positive outcome turning points, negative outcome turning points, formal turning points, and young people who could not identify any relational turning points. Young people who described a negative turning point or who were unable to identify a turning point were less involved and invested in romantic relationships. In addition, they reported a greater number of depressive symptoms. Those who described a positive outcome turning point or who pointed at a formal turning point reported more stable and healthy romantic relationships and a lower number of symptoms. Increased immature dependency and stress associated with goal attainment measured seven years earlier explained the tendency to identify a negative turning point or the inability to point to a significant event. Conceptualized within the reflexive model of transitions, findings suggest that personal assets such as personality attributes and developmental goal pursuit explain the ability or difficulty of young people to capture the meaning of events in their relational involvements and to move toward or interfere with settling down.     

Predictive comparison of joint longitudinal-survival modeling: a case study illustrating competing approaches

The joint modeling of longitudinal and survival data has received extraordinary attention in the statistics literature recently, with models and methods becoming increasingly more complex. Most of these approaches pair a proportional hazards survival with longitudinal trajectory modeling through parametric or nonparametric specifications. In this paper we closely examine one data set previously analyzed using a two parameter parametric model for Mediterranean fruit fly (medfly) egg-laying trajectories paired with accelerated failure time and proportional hazards survival models. We consider parametric and nonparametric versions of these two models, as well as a proportional odds rate model paired with a wide variety of longitudinal trajectory assumptions reflecting the types of analyses seen in the literature. In addition to developing novel nonparametric Bayesian methods for joint models, we emphasize the importance of model selection from among joint and non joint models. The default in the literature is to omit at the outset non joint models from consideration. For the medfly data, a predictive diagnostic criterion suggests that both the choice of survival model and longitudinal assumptions can grossly affect model adequacy and prediction. Specifically for these data, the simple joint model used in by Tseng et al. (Biometrika 92:587–603, 2005) and models with much more flexibility in their longitudinal components are predictively outperformed by simpler analyses. This case study underscores the need for data analysts to compare on the basis of predictive performance different joint models and to include non joint models in the pool of candidates under consideration.