Testing drug additivity based on monotherapies

Under the Loewe additivity, constant relative potency between two drugs is a sufficient condition for the two drugs to be additive. Implicit in this condition is that one drug acts like a dilution of the other. Geometrically, it means that the dose‐response curve of one drug is a copy of another that is shifted horizontally by a constant over the log‐dose axis. Such phenomenon is often referred to as parallelism. Thus, testing drug additivity is equivalent to the demonstration of parallelism between two dose‐response curves. Current methods used for testing parallelism are usually based on significance tests for differences between parameters in the dose‐response curves of the monotherapies. A p‐value of less than 0.05 is indicative of non‐parallelism. The p‐value‐based methods, however, may be fundamentally flawed because an increase in either sample size or precision of the assay used to measure drug effect may result in more frequent rejection of parallel lines for a trivial difference. Moreover, similarity (difference) between model parameters does not necessarily translate into the similarity (difference) between the two response curves. As a result, a test may conclude that the model parameters are similar (different), yet there is little assurance on the similarity between the two dose‐response curves. In this paper, we introduce a Bayesian approach to directly test the hypothesis that the two drugs have a constant relative potency. An important utility of our proposed method is in aiding go/no‐go decisions concerning two drug combination studies. It is illustrated with both a simulated example and a real‐life example. Copyright © 2015 John Wiley & Sons, Ltd.     

Implementing solutions to barriers to on-site HIV testing in substance abuse treatment: A tale of three facilities

Due to the scarcity of resources for implementing rapid onsite HIV testing, many substance abuse treatment programs do not offer these services. This study sought to determine whether addressing previously identified implementation barriers to integrating on-site rapid HIV testing into the treatment admissions process would increase offer and acceptance rates. Results indicate that it is feasible to integrate rapid HIV testing into existing treatment programs for substance abusers when resources are provided. Addressing barriers such as providing start-up costs for HIV testing, staff training, addressing staffing needs to reduce competing job responsibilities, and helping treatment staff members overcome their concerns about clients’ reactions to positive test results is paramount for the integration and maintenance of such programs.     

Rasch Analysis of the Metacognitive Awareness Listening Questionnaire (MALQ)

A valid metacognitive awareness second language (L2) listening questionnaire is important for both researchers and teachers to facilitate the measurement of language learners’ ability to reflect on and direct their L2 learning. However, very few metacognitive awareness questionnaires have been validated, particularly in the area of L2 listening (cf., Vandergrift, Goh, Mareschal, & Tafaghodtari, 2006). The Metacognitive Awareness Listening Questionnaire (MALQ) (Vandergrift et al.) is one exception. However, very little information has been collected on the MALQ’s psychometric properties. To address this paucity, we administered the MALQ to a sample of 299 male Korean adolescent speakers of English. Using a modern measurement approach to scale validation (Rasch modeling), we found that with the exception of one subscale (Person knowledge) the subscales had good psychometric properties in that it was reliable and unidimensional.     

Barriers to accessing HIV and sexual health services among gay men in Tasmania,Australia

We examined barriers to accessing HIV and sexual health services among gay and bisexual men (GBM) in Tasmania, Australia, using in-depth interviews. Most participants were satisfied with the care they had received at public sexual health services. Barriers included the limited number of services, concerns about anonymity and privacy in small communities, difficulties accessing services via a general practitioner, and perceived stigma and discrimination. Improving the accessibility and availability of HIV and sexual health services in Tasmania is crucial to promote the engagement of GBM, which could be achieved via combined efforts of government services and community organizations.     

A nonparametric mixture approach to density and null proportion estimation in large-scale multiple comparison problems

A new method for estimating the proportion of null effects is proposed for solving large-scale multiple comparison problems. It utilises maximum likelihood estimation of nonparametric mixtures, which also provides a density estimate of the test statistics. It overcomes the problem of the usual nonparametric maximum likelihood estimator that cannot produce a positive probability at the location of null effects in the process of estimating nonparametrically a mixing distribution. The profile likelihood is further used to help produce a range of null proportion values, corresponding to which the density estimates are all consistent. With a proper choice of a threshold function on the profile likelihood ratio, the upper endpoint of this range can be shown to be a consistent estimator of the null proportion. Numerical studies show that the proposed method has an apparently convergent trend in all cases studied and performs favourably when compared with existing methods in the literature.     

Two-Tailed p-Values and Coherent Measures of Evidence

ABSTRACT

In a test of significance, it is common practice to report the p-value as one way of summarizing the incompatibility between a set of data and a proposed model for the data constructed under a set of assumptions together with a null hypothesis. However, the p-value does have some flaws, one being in general its definition for two-sided tests and a related serious logical one of incoherence, in its interpretation as a statistical measure of evidence for its respective null hypothesis. We shall address these two issues in this article.     

Replication with MTurk of the experimental design by Gangadharan,Grossman, Jones & Leister (2018): Charitable giving across donor types

Understanding the motivations behind charitable giving and the identification of donor types have aroused growing interest among researchers. The economic literature has highlighted the model of pure altruist and subsequently the more realistic model of impure altruist or warm-glow giver. The need to distinguish and empirically identify these types of donors has given rise to some economic experiments. This paper - using the platform by Amazon's Mechanical Turk with a large sample of participants (N = 1062) - shows the findings of a near replication of the experimental design by Gangadharan et al. (2018). Results are consistent with the original study and confirm the validity of the procedure and the ability to replicate a critical feature of the original design.     

Moving college health research forward: Reconsidering our reliance on statistical significance testing

Understanding the unique health needs of college students and establishing best practices to address them depend, heavily, on the inherent quality and contribution of the research identifying these needs. College health-focused publications currently exemplify less than ideal statistical reporting practices. Specifically, college health practitioners and researchers continue to rely heavily upon null hypothesis significance testing (NHST) as the sole standard for effectiveness, validity, and/or replicability of scientific studies, even though NHST itself was not designed for such purposes. Herein we address the following questions: (a) What is NHST? (b) What are the inherent limitations of NHST? (c) What are recommended alternatives to NHST? and (d) How can editorial policies promote adopting NHST alternatives? Using college health data from the CORE 2011 Alcohol and Drug survey, we provide a heuristic example demonstrating how effect sizes do not suffer from the same limitations as NHST.     

Pre-checking for non-monotonicity of the Wald statistic

The non-monotonic behaviour of the Wald test in some finite-sample applications leads to low power when the null hypothesis needs rejection most. This article proposes a simple check for discerning if the Wald statistic for testing significance of regression coefficients is non-monotonic in the neighbourhood of the parameter space from which the sample data are drawn. Monte Carlo simulations show that this method works rather well for detecting situations where the Wald test can be safely applied. An example is provided to illustrate the use of this check.