Complete ranking procedures with quadratic loss

Suppose that one wishes to rank k normal populations, each with common variance σ² and unknown means θ_i (i=1,2,…,k). Independent samples of size n are taken from each population, and the sample averages are used to rank the populations. In this paper, we investigate what sample sizes, n, are necessary to attain “good” rankings under various loss functions. Section discusses various loss functions and their interpretation. Section 2 gives the solution for a reasonable non-parametric loss function. Section 3 gives the solution for a reasonable parameteric loss function.     

Bootstrap and permutation rank tests for proportional hazards under right censoring

We address the testing problem of proportional hazards in the two-sample survival setting allowing right censoring, i.e., we check whether the famous Cox model is underlying. Although there are many test proposals for this problem, only a few papers suggest how to improve the performance for small sample sizes. In this paper, we do exactly this by carrying out our test as a permutation as well as a wild bootstrap test. The asymptotic properties of our test, namely asymptotic exactness under the null and consistency, can be transferred to both resampling versions. Various simulations for small sample sizes reveal an actual improvement of the empirical size and a reasonable power performance when using the resampling versions. Moreover, the resampling tests perform better than the existing tests of Gill and Schumacher and Grambsch and Therneau . The tests’ practical applicability is illustrated by discussing real data examples.

     

Revisiting the Role of Impulsivity and Compulsivity in Problematic Sexual Behaviors

Impulsivity and compulsivity are transdiagnostic features associated with clinically relevant aspects of psychiatric disorders, including addictions. However, little research has investigated how impulsivity and compulsivity relate to hypersexuality and problematic pornography use. Thus, the aims of the present study were to investigate (a) self-reported impulsivity and compulsivity with respect to hypersexuality and problematic pornography use and (b) the similarities and possible differences between hypersexuality and problematic pornography use in these domains. Utilizing structural equation modeling (SEM) in a large community sample (N = 13,778 participants; female = 4,151, 30.1%), results indicated that impulsivity (β = .28, β = .26) and compulsivity (β = .23, β = .14) were weakly related to problematic pornography use among men and women, respectively. Impulsivity had a stronger relationship (β = .41, β = .42) with hypersexuality than did compulsivity (β = .21, β = .16) among men and women, respectively. Consequently, impulsivity and compulsivity may not contribute as substantially to problematic pornography use as some scholars have proposed. On the other hand, impulsivity might have a more prominent role in hypersexuality than in problematic pornography use. Future research should examine further social and situational factors associated with problematic pornography use.     

Cooperative production with unequal skills: The solidarity approach to compensation

We consider a simple production model and we assume that agents have unequal production skills which can in no way be attributed to their responsibility. We study how it is possible, if at all, to compensate for differential skills by applying Rawls's idea of a collective sharing in the benefits of skills. For this purpose, we introduce an axiom of solidarity, according to which agents should all be affected in the same direction if the profile of personal skills changes. We show that particular allocation rules are characterized be combining this axiom with a requirement of non-discrimination among preferences, or with a property capturing Nozick's idea of guaranteeing a minimal benefit from one's own skill. Received: 1 July 1996/Accepted: 25 May 1998     

A Longitudinal Analysis of Adolescent Substance Use and School Motivation Among African American Youth

Cross‐sectional research has shown a link between adolescent substance use and educational motivation. The purpose of the current study was to examine this link in a longitudinal sample of African American youth. The study examined the interrelationships between alcohol and both marijuana use and school motivation over the high school years and their effect on graduation in 681 African American adolescents (50.8% female). School motivation was shown to relate to subsequent alcohol use throughout high school and marijuana use early in high school. School motivation did not affect graduation status, but alcohol and marijuana use were related to a lower likelihood of graduating from high school. Some gender differences and differences among those who had tried alcohol or marijuana at the first wave as opposed to those who had not tried each substance were found. The findings support a systems model where school experiences can affect substance use, which, in turn, can affect the completion of high school.     

Subjective Well-Being and Social Capital in Belgian Communities. The Impact of Community Characteristics on Subjective Well-Being Indicators in Belgium

In this article, we investigate the effect of individual and community level characteristics on subjective well-being in Belgium. Various indicators for subjective well-being are being used in a multilevel analysis of the 2009 SCIF survey (n = 2,080) and the 2006 Belgian ESS sample (n = 1,798). On the individual level, most hypotheses on the determinants of subjective well-being were confirmed. Living with a partner and age were shown to have strong effects, but also social capital indicators had a significant positive effect on subjective well-being. All these effects remained significant controlling for optimism. On the community level, especially unemployment rate had a negative impact on subjective well-being. The analysis further demonstrates that in homogeneous regions, community characteristics have a far weaker impact on subjective well-being indicators than in economically more heterogeneous regions.     

Réinterroger la relation entre école et mobilité sociale. Le cas des enfants d’agriculteurs et d’ouvriers dans l’Ouest

Till now, the relation between schooling and social mobility, a classical question in the sociology of education, has been approached through analyses of a structural sort, either by focusing on the functions that schools are supposed to fill or by adopting the timeless model of neoclassical economics. This approach does not examine all possible relations between schools and social mobility; nor does it see these relations in terms of a process. A study of the scholastic biographies of the children of farmers and workers in western France renews our conception of this relation. It shows that this relation mainly stems from a combination of quite heterogeneous elements, which we glimpse in these biographies.