Estimating correlations with missing data,a bayesian approach

The posterior distribution of the bivariate correlation is analytically derived given a data set wherex is completely observed buty is missing at random for a portion of the sample. Interval estimates of the correlation are then constructed from the posterior distribution in terms of highest density regions (HDRs). Various choices for the form of the prior distribution are explored. For each of these priors, the resulting Bayesian HDRs are compared with each other and with intervals derived from maximum likelihood theory.     

Family‐Based HIV and Sexually Transmitted Infection Risk Reduction for Drug‐Involved Young Offenders: 42‐Month Outcomes

This study tested a family‐based human immunodeficiency virus (HIV)/sexually transmitted infection (STI) prevention approach integrated within an empirically supported treatment for drug‐involved young offenders, Multidimensional Family Therapy (MDFT). A randomized, controlled, two‐site community‐based trial was conducted with 154 youth and their parents. Drug‐involved adolescents were recruited in detention, randomly assigned to either MDFT or Enhanced Services as Usual (ESAU), and assessed at intake, 3, 6, 9, 18, 24, 36, and 42‐month follow‐ups. Youth in both conditions received structured HIV/STI prevention in detention and those in MDFT also received family‐based HIV/STI prevention as part of ongoing treatment following detention release. Youth in both conditions and sites significantly reduced rates of unprotected sex acts and STI incidence from intake to 9 months. They remained below baseline levels of STI incidence (10%) over the 42‐month follow‐up period. At Site A, adolescents who were sexually active at intake and received MDFT showed greater reduction in overall frequency of sexual acts and number of unprotected sexual acts than youth in ESAU between intake and 9‐month follow‐ups. These intervention differences were evident through the 42‐month follow‐up. Intervention effects were not found for STI incidence or unprotected sex acts at Site B. Intensive group‐based and family intervention in detention and following release may reduce sexual risk among substance‐involved young offenders, and a family‐based approach may enhance effects among those at highest risk. Site differences in intervention effects, study limitations, clinical implications, and future research directions are discussed.     

The Influence of Skills,Message Frame,and Visual Aids on Prevention of Sexually Transmitted Diseases

In a large three week longitudinal study, we investigated the efficacy of framed messages for promoting condom use in sexually active young adults. We also investigated the influence of key risk literacy skills (i.e., numeracy and graph literacy) and visual aids (i.e., icon arrays) on the efficacy of framed messages. Finally, we investigated the underlying psychological mechanisms of behavioral change on the ability of icon arrays to improve message effectiveness. Results showed that framed messages including icon arrays increased adherence to self‐reported condom use by giving rise to enduring changes in attitudes and behavioral intentions, which influenced behavior. Icon arrays were found to be most beneficial among young adults with relatively low numeracy as long as they had high graph literacy. These findings build on the previous research in risk communication and extend psychological theories of health‐related decision making such as the theory of planned behavior. These findings also map the conditions under which well‐constructed visual aids can be among the most effective, transparent, and ethically desirable means of risk communication. Implications for risk communication and informed medical decision making are discussed. Copyright © 2013 John Wiley & Sons, Ltd.     

The Act Frequency Approach to the study of impulsivity

Though widely used in research on personality, the impulsivity construct is far from being well defined. Different ways of measuring and operationalizing this construct have led to contradictory empirical results. Nor is it clear where impulsivity belongs in multidimensional personality models. For instance, in Eysenck's original scheme it is treated as a component of extroversion, whereas in Costa and McCrae's (1992) NEO model it is a facet of the neuroticism dimension. In this study, we used Buss and Craik's Act Frequency Approach to investigate the components of impulsivity and its relationships (at both internal and manifested structure levels) with extroversion and neuroticism. A set of acts was identified, the frequency of commission of which correlated with other measures of impulsivity (especially its motor and cognitive aspects), and correlated better with neuroticism than with extroversion.     

Is the Ambivalence a Sign of the Multiple-Self Nature of the Human Being? Interdisciplinary Remarks

Ambivalence is a constituent feature of human beings. The aim of this article is to systematise the fundamental sources of ambivalence (neuropsychic, socio-cultural and situational) and highlight that ambivalence can be considered as an external sign or manifestation of a complex and multiple internal human nature; that is, a human being constituted by multiple selves. In this paper the self is viewed as a principle of organization and integration for action, that is, as a complex neurological process and not as a static entity. The purpose is to show how by assuming ambivalence and the multiple-self, social and anthropological theories can offer a more realistic view of human beings.     

A Formal Ontological Theory Based on Timeless Events

I offer a formal ontological theory where the basic building blocks of the world are timeless events. The composition of events results in processes. Spacetime emerges as the system of all events. Things are construed as bundles of processes. I maintain that such a view is in accord with General Relativity and offers interesting prospects for the foundations of classical and quantum gravity.     

Using cognitive learning theory to design effective on-line statistics tutorials

Careful attention to principles of learning can improve the design of Web-based lessons and tutorials. Tutorials from the Web Interface for Statistics Education (WISE; http://wise.cgu.edu) demonstrate how specific principles can be integrated into Web design to enhance learning in two areas. First, the impact of students’ poor self-regulation abilities on Web-based learning is considered. Second, evidence that specific types of visual presentations improve learning is discussed. Finally, the need for empirical evaluation is emphasized. Specific research and examples from the WISE project are used to illustrate each of these points.     

The efficacy of postdivorce intervention programs for children: A meta-analytical review

Preventive postdivorce interventions aim to help children cope with divorce and promote their adjustment. Nevertheless, questions remain regarding the concrete outcomes of these interventions and the intervention characteristics that influence them. This meta-analysis of 30 studies analyzes the efficacy of postdivorce interventions on children's symptomatology, personal resources, and adaptation to divorce. Likewise, it explores whether the intervention impacts the putative mediators from the family context and whether the characteristics of the studies themselves also influence the results. Using a data set of N = 4344 individuals, 258 effect sizes were calculated. Random effects analyses evidenced the impact of the interventions on specific variables instead of on children's global adjustment. There were no significant effects on children's mental health outcomes, and none of these effects were qualified by the moderators that were examined. Preventive postdivorce interventions had significant effects, specifically on children's divorce adjustment and self-esteem. The study of the moderators found that the interventions were generally homogeneous, and only one of the 20 moderators examined had a significant effect. Based on children's age, the interventions had an impact on family functioning only when they involved younger children, but this result should be interpreted with caution due to the small sample of studies. This meta-analysis provides evidence of the relevance of postdivorce interventions to critical variables as well as information about the role of the intervention characteristics in the effects and makes suggestions for future research on divorce interventions that encompass both practical and empirical developments.