An adaptive randomized design with application to estimation

When allocating observations to two populations for estimation or testing, the optimal proportion of the data that should be allocated to the first population, if it exists, often depends on unknown parameters. Adaptive designs have thus been proposed, in which allocation of the next observation is based on an estimate of the optimal proportion computed from the data already gathered. The authors introduce a simple randomized adaptive design and give some of its properties. Applications are given to estimating the difference of two success probabilities, and the difference of two normal means.     

Animal Rights Talk: Moral Debate over the Internet

Messages sent over Animal Rights-Talk, an electronic mail network devoted to the discussion of issues related to the animal rights movement, were analyzed. Messages typically fell into the following categories: questions and information, discussions of philosophical issues, ethical problems associated with the treatment of particular species, the politics of the animal rights movement, problems of moral consistency, the ethics of particular uses of non-human species (e.g., meat consumption, biomedical research with animal subjects), and matters pertaining to the internal life of the network (e.g., efforts at control of perceived norm violations). Debates between animal activists and animal researchers over the network often reflected the conflicting cosmologies of scientists and animal protectionists. We argue that computer bulletin boards offer a potentially important avenue for qualitative research.     

Arbitrage and global cones: Another counterexample

Chichilnisky (1997) claims that another variant of her condition limiting arbitrage is necessary and sufficient for existence of equilibrium and nonemptiness of the core in an economy with short sales allowing half lines in indifference surfaces. Her proof, however, is based on a proposition purporting to relate her notion of “global cone” (see Chichilnisky (1997) for references) to the Page-Wooders “increasing cone.” In this paper, we present a counterexample showing that parts (i) and (ii) of Chichilnisky's proposition are false. Thus, Chichilnisky's claimed result is without proof. Received: 18 August 1997/Accepted: 30 January 1998     

Nonsuicidal Self-injury in a College Population: General Trends and Sex Differences

Abstract

Objective: To describe basic nonsuicidal self-injury (NSSI) characteristics and to explore sex differences. Methods: A random sample from 8 universities were invited to participate in a Web-based survey in 2006–2007; 38.9% (n = 14,372) participated. Analysis assessed sex differences in NSSI prevalence, practices, severity, perceived dependency, and help-seeking; adjusted odds ratios for NSSI characteristics were calculated by sex status. Results: Lifetime NSSI prevalence rates averaged 15.3%. Females were more likely than males to self-injure because they were upset (adjusted odds ratio [AOR] = 1.6; 95% confidence interval [CI] = 1.3–2.1) or in hopes that someone would notice them (AOR = 1.6, 95% CI = 1.1–2.7). Males were 1.6 times (95% CI = 1.2–2.2) more likely to report anger and 4.0 times (95% CI = 2.3–6.8) more likely to report intoxication as an initiating factor. Sexual orientation predicted NSSI, particularly for women (Wald F = 8.81, p ≤ .000). Only 8.9% of the NSSI sample reported disclosing NSSI to a mental health professional. Conclusions: NSSI is common in college populations but varies significantly by sex and sexual orientation. NSSI disclosure is low among both sexes.     

The Role of Religion and Stress in Sexual Identity and Mental Health Among Lesbian,Gay, and Bisexual Youth

This study investigated religious stress, gay‐related stress, sexual identity, and mental health outcomes in lesbian, gay, and bisexual (LGB) adolescents and emerging adults. The model examined negative LGB identity as a mediator of the relationships between (1) religious stress and mental health, and (2) gay‐related stress and mental health. The data indicated that negative LGB identity fully accounted for both relationships. Findings suggest that a negative sense of sexual identity for LGB youth helps explain the links between religious and gay‐related stressors and mental health. As LGB youth may have limited control over these stressors, the importance of helping LGB youth maintain a positive LGB identity, despite homonegative messages from others, is discussed.     

Response adaptive designs that incorporate switching costs and constraints

This paper examines the design and performance of sequential experiments where extensive switching is undesirable. Given an objective function to optimize by sampling between Bernoulli populations, two different models are considered. The constraint model restricts the maximum number of switches possible, while the cost model introduces a charge for each switch. Optimal allocation procedures and a new “hyperopic” procedure are discussed and their behavior examined. For the cost model, if one views the costs as control variables then the optimal allocation procedures yield the optimal tradeoff of expected switches vs. expected value of the objective function.