Can we disregard the whole model? Omnibus non-inferiority testing for R2 in multi-variable linear regression and in ANOVA

Determining a lack of association between an outcome variable and a number of different explanatory variables is frequently necessary in order to disregard a proposed model (i.e., to confirm the lack of a meaningful association between an outcome and predictors). Despite this, the literature rarely offers information about, or technical recommendations concerning, the appropriate statistical methodology to be used to accomplish this task. This paper introduces non-inferiority tests for ANOVA and linear regression analyses, which correspond to the standard widely used F test for and R², respectively. A simulation study is conducted to examine the Type I error rates and statistical power of the tests, and a comparison is made with an alternative Bayesian testing approach. The results indicate that the proposed non-inferiority test is a potentially useful tool for ‘testing the null’.     

Mobile Communication and Civil Society: Linking Patterns and Places of Use to Engagement with Others in Public

This study examined whether and how mobile communication influences the extent to which one engages with new people in public settings. Contrary to our expectation, general use of the technology in public did not detract from conversing with strangers. Shifting focus from where one uses the mobile phone to how it is used, we found that uses for coordination and news each lead to increased conversations with strangers in public settings, while relational use detracted from them. The findings also reveal an interactive effect such that those who use mobile technology for news and frequently use it in public were more likely to engage with strangers in public. The discussion offers interpretation of the findings and directions for future research.     

Comorbid Substance Use and Anxiety Disorders in Adolescents

To explore the coexistence of substance use disorders and anxiety disorders in adolescents, we assessed adolescents presenting for treatment to an inpatient substance abuse treatment facility (SUH), an inpatient psychiatric treatment facility (IPH), and a community-based psychiatric facility (CMHC) for comorbid substance use and psychiatric diagnoses. Thirty subjects from each facility (N=90) were interviewed using the revised Child Schedule for Affective Disorders and Schizophrenia (K-SADS) and the Structured Clinical Interview DSM-III-R (SCID-R) for substance use diagnoses. Overall, comorbidity (anxiety and substance use disorders) prevalence was 67% (20/30) of adolescents in the SUH group, 33% (10/30) of the CMHC adolescents, and 33% (10/30) of the IPH adolescents. Alcohol and marijuana were the most frequently abused substances. Anxiety disorders commonly coexist with substance use disorders in adolescents. Early identification and treatment of anxiety disorders may in fact prevent substance abuse in this population.     

Religion and the body in medical research

Religious discussion of human organs and tissues has concentrated largely on donation for therapeutic purposes. The retrieval and use of human tissue samples in diagnostic, research, and education contexts have, by contrast, received very little direct theological attention. Initially undertaken at the behest of the National Bioethics Advisory Commission, this essay seeks to explore the theological and religious questions embedded in nontherapeutic use of human tissue. It finds that the "donation paradigm" typically invoked in religious discourse to justify uses of the body for therapeutic reasons is inadequate in the context of nontherapeutic research, while the "resource paradigm" implicit in scientific discourse presumes a reductionist account of the body that runs contrary to important religious values about embodiment. The essay proposes a "contribution paradigm" that provides a religious perspective within which research on human tissue can be both justified and limited.