Three Bartlett-type corrections for score statistics in symmetric nonlinear regression models

We present simple matrix formulae for corrected score statistics in symmetric nonlinear regression models. The corrected score statistics follow more closely a χ ² distribution than the classical score statistic. Our simulation results indicate that the corrected score tests display smaller size distortions than the original score test. We also compare the sizes and the powers of the corrected score tests with bootstrap-based score tests.     

Re‐invigorating democracy?: White middle class identities and comprehensive schooling

Recent research on social class and whiteness points to disquieting and exclusive aspects of white middle class identities. This paper focuses on whether ‘alternative’ middle class identities might work against, and disrupt, normative views of what it means to be ‘middle class’ at the beginning of the 21^st Century. Drawing on data from those middle classes who choose to send their children to urban comprehensives, we examine processes of ‘thinking and acting otherwise’ in order to uncover some of the commitments and investments that might make for a renewed and reinvigorated democratic citizenry. The difficulties of turning these commitments and investments into more equitable ways of interacting with class and ethnic others which emerge as real challenges for this left leaning, pro‐welfare segment of the middle classes. Within a contemporary era of neo‐liberalism that valorises competition, individualism and the market even these white middle classes who express a strong commitment to community and social mixing struggle to convert inclinations into actions.     

Parental Residential and Partnering Transitions and the Initiation of Adolescent Romantic Relationships

This study focused on the possible links between parental residential and partnering transitions (a parent's move out of the household, introduction of a new maternal and paternal partner) and the initiation of romantic relationships in adolescence. Using data from a prospective cohort study of Dutch adolescents (the TRacking Adolescents' Individual Lives Survey; N = 1,513), recurrent event discrete‐time models with random effects were estimated, controlling for the initial family structure and quality of family climate. The results demonstrated that when all 3 events were considered, only the initiation of a new romantic relationship by the mother was associated with an increase in the odds of initiating a romantic relationship for the adolescent.     

The Effect of Children on Men’s and Women’s Chances of Re-partnering in a European Context

This work examines what role children play in the re-partnering process in five European countries (Norway, France, Germany, Romania, and the Russian Federation) by addressing the following research questions: (1) To what extent do men and women differ in their re-partnering chances?; (2) Can gender differences in re-partnering be explained by the presence of children?; (3) How do the custodial arrangements and the child’s age affect the re-partnering chances of men and women? We use the partnership and parenthood histories of the participants in the first wave of the Generations and Gender Survey (United Nations, Generations and Gender Programme: Survey Instruments. United Nations, New York/Geneva, 2005) to examine the transition to moving in with a new partner following the dissolution of the first marital union, separately for men and women. The story that emerges is one of similarities in the effects rather than differences. In most countries, men are more likely to re-partner than women. This gender difference can be attributed to the presence of children as our analyses show that childless men and women do not differ in their probability to re-partner. Mothers with resident children are less likely to re-partner than non-mothers and a similar though often non-significant effect of resident children is observed for fathers. In most countries we find that as the child ages, the chances to enter a new union increase. In sum, our study indicates that children are an important factor in re-partnering and a contributor to the documented gender gap in re-partnering, and this holds throughout distinct institutional and cultural settings.     

"Anything Can Happen With Police Around": Urban Youth Evaluate Strategies of Surveillance in Public Places

In order to document urban youth experiences of adults in positions of public authority, including police, educators, social workers and guards, a broad based street survey of 911 New York City-based urban youth was conducted in which youth, stratified by race, ethnicity, gender and borough, were asked about their experiences with, attitudes toward, and trust of adult surveillance in communities and in schools. In-depth telephone interviews were conducted with 36 youth who have experienced serious, adverse interactions with police, guards, or educators. Findings suggest that urban youth, overall, express a strong sense of betrayal by adults and report feeling mistrusted by adults, with young men of color most likely to report these perceptions.     

Joint models with multiple longitudinal outcomes and a time-to-event outcome: a corrected two-stage approach

Joint models for longitudinal and survival data have gained a lot of attention in recent years, with the development of myriad extensions to the basic model, including those which allow for multivariate longitudinal data, competing risks and recurrent events. Several software packages are now also available for their implementation. Although mathematically straightforward, the inclusion of multiple longitudinal outcomes in the joint model remains computationally difficult due to the large number of random effects required, which hampers the practical application of this extension. We present a novel approach that enables the fitting of such models with more realistic computational times. The idea behind the approach is to split the estimation of the joint model in two steps: estimating a multivariate mixed model for the longitudinal outcomes and then using the output from this model to fit the survival submodel. So-called two-stage approaches have previously been proposed and shown to be biased. Our approach differs from the standard version, in that we additionally propose the application of a correction factor, adjusting the estimates obtained such that they more closely resemble those we would expect to find with the multivariate joint model. This correction is based on importance sampling ideas. Simulation studies show that this corrected two-stage approach works satisfactorily, eliminating the bias while maintaining substantial improvement in computational time, even in more difficult settings.