Valid Randomization for Models with Neighbour Effects From Treatments

Valid methods of randomization have been proposed for several classes of neighbour-balanced designs, but the assumed models did not include the neighbour effects from treatments. We present sufficient conditions for such randomizations to be also valid for direct and neighbour effects simultaneously. It is shown through several examples that these sufficient conditions can be satisfied for uni- or bi-directional neighbour effects, provided a particular block structure is used. The covariance between estimators of direct and neighbour effects over the randomization is also studied.     

The Effects of Traditional Family and Gender Ideology on Earnings: Race and Gender Differences

Despite increasing gains in labor market opportunities, women and racial minorities earn less than their white male counterparts. Using data from the National Longitudinal Survey of Youth, this study explores racial and gender variation in how family and gender ideology shape this wage gap. The findings reveal that traditional role attitudes reduce earnings for African American men, African American women, and white women. However, white women experience the largest threat to wages as a result of conventional gender ideology. Further, the number of children and the timing of childbearing are detrimental to black and white women’s earnings, while neither of these factors hampers men’s earnings.C. André Christie-Mizell, Department of Sociology, University of Akron, 258 Olin Hall, Akron, OH 44325-1905, USA; e-mail: mizell@uakron.edu.     

Psychological characteristics of volunteers in studies on gambling

Advertisements were published in local newspapers asking for volunteers to participate in a study on gambling. A battery of eleven questionnaires was mailed to the subjects assessing pathological gambling behavior, sociodemographic characteristics, motivation to gamble, erroneous perceptions about gambling, superstitious beliefs, depressive symptoms, social anxiety and avoidance, alcohol and drug abuse, problem-solving skills, and marital satisfaction. Subjects received $10 when they returned the questionnaires fully completed. Response rate was over 95%. Surprisingly, 29% of the respondents met the criterion for probable pathological gambling (score of 5 or more on the SOGS) and a further 16% were identified as potential pathological gamblers (scores of 3 or 4). The potential and probable pathological gamblers showed significant differences on motivational and cognitive variables related to gambling compared to those subjects who showed no signs of pathological gambling. The probable pathological gamblers reported significantly more signs of poor psychosocial functioning than the other two groups, including depressive symptoms, poor problem orientation, drug and alcohol abuse, and interpersonal conflict. The practical and theoretical implications of these results are discussed.     

Parental Divorce and Offspring Depressive Symptoms: Dutch Developmental Trends During Early Adolescence

In this study, we investigated if the association between parental divorce and depressive symptoms changes during early adolescence and if developmental patterns are similar for boys and girls. Data were collected in a prospective population cohort of Dutch adolescents (N = 2,149), aged 10 – 15 years. Outcome variables were self‐reported and parent‐reported depressive symptoms. The effects of divorce were adjusted for parental depression. In both self‐reported and parent‐reported data, we found a three‐way interaction of gender, age, and parental divorce, indicating that with increasing age, parental divorce became more strongly associated with depressive symptoms among girls, but not boys. These results suggest that girls with divorced parents are at particularly high risk to develop depressive symptoms during adolescence.     

Análisis de la contextualización del comportamiento adaptativo en el retraso mental: Comparación entre contexto familiar e institucional

Resumen

Este estudio se dirige a contrastar las diferencias en el comportamiento adaptativo de los sujetos retrasados que son producto de los diferentes contextos en los que éste es emitido. En este caso, el contexto se entiende como los aspectos físicos y sociales del lugar en el que inmediatamente se produce la conducta. Esta perspectiva molecular del contexto ha permitido detectar diferencias en el comportamiento adaptativo en términos de lenguaje receptivo y lenguaje expresivo. La muestra utilizada fueron 71 sujetos evaluados a través del West Virginia assessment and tracking system.     

A Case Study of De-randomization Methods for Combinatorial Approximation Algorithms

We study three different de-randomization methods that are often applied to approximate combinatorial optimization problems. We analyze the conditional probabilities method in connection with randomized rounding for routing, packing and covering integer linear programming problems. We show extensions of such methods for non-independent randomized rounding for the assignment problem. The second method, the so-called random walks is exemplified with algorithms for dense instances of some NP problems. Another often used method is the bounded independence technique; we explicit this method for the sparsest cut and maximum concurrent flow problems.     

A multivariate uniformity test for the case of unknown support

A test for the hypothesis of uniformity on a support S⊂ℝ ^d is proposed. It is based on the use of multivariate spacings as those studied in Janson (Ann. Probab. 15:274–280, 1987). As a novel aspect, this test can be adapted to the case that the support S is unknown, provided that it fulfils the shape condition of λ-convexity. The consistency properties of this test are analyzed and its performance is checked through a small simulation study. The numerical problems involved in the practical calculation of the maximal spacing (which is required to obtain the test statistic) are also discussed in some detail.     

New algorithms for k-center and extensions

The problem of interest is covering a given point set with homothetic copies of several convex containers C ₁,…,C _k , while the objective is to minimize the maximum over the dilatation factors. Such k-containment problems arise in various applications, e.g. in facility location, shape fitting, data classification or clustering. So far most attention has been paid to the special case of the Euclidean k-center problem, where all containers C _i are Euclidean unit balls. Recent developments based on so-called core-sets enable not only better theoretical bounds in the running time of approximation algorithms but also improvements in practically solvable input sizes. Here, we present some new geometric inequalities and a Mixed-Integer-Convex-Programming formulation. Both are used in a very effective branch-and-bound routine which not only improves on best known running times in the Euclidean case but also handles general and even different containers among the C _i .     

Characterizations of discrete distributions based on conditional expectations of record values

r -th record values subject to (r + 1)-th record values, record mean function, from a distribution of discrete type. We give some properties of the record mean function and an explicit expression for the distribution function based on its record mean function, which allows us to characterize particular discrete distributions using the record mean functions. Received: January 4, 1999; revised version: September 27, 1999