A network algorithm for the exact treatment of the 2×k contingency table

A common statistical problem encountered in biomedical research is to test the hypothesis that the parameters of k binomial populations are all equal. An exact test of significance of this hypothesis is possible in principle, the appropriate null distribution being a normalized product of k binomial coefficients. However, the problem of computing the tail area of this distribution can be formidable since it requires the enumeration of all sets of k binomial coefficients whose product is less than a given constant. Existing algorithms, all of which rely on explicit enumeration to generate feasible binomial coefficients     

An Extension of the Normal/Independent Family for Studies of Robust Estimators

The family of normal scale mixture distributions, also called the Normal/Independent family, has been used for efficient Monte Carlo studies of robust estimators. The distributions in this family are unimodal. The Normal/Independent family is extended by introducing a location mixing in addition to the scale mixing. Distributions in this extension may be nonunimodal. The asymptotic variances of robust estimators of location are compared using the distributions from the extension. A Monte Carlo swindle similar to the one used in the Princeton study is given for the extended family. A small simulation study demonstrates the efficiency of the swindle. The swindle is compared with other swindle methods based on Fisher's score function and regression.     

Toward an emergent Asian behavioural model of perceived managerial and leadership effectiveness: a cross-nation comparative analysis of effective and ineffective managerial behaviour of private sector managers in India and South Korea

ABSTRACT

This Type 4 (emic-and-etic) indigenous cross-case/cross-nation comparative study compares the results of two Type 3 (emic-as-emic) indigenous replication studies of effective and ineffective managerial behaviour carried out within private companies in India and South Korea respectively. The method used was ‘realist qualitative content analysis’ involving inductive open and axial coding. Of the Indian findings 100% were found to be convergent in meaning with 94.43% of the equivalent South Korean findings. This has led to the identification of a two-factor emergent Asian behavioural model of perceived managerial and leadership effectiveness comprised of 16 positive (effective) and 6 negative (ineffective) generic behavioural criteria. These criteria could be used in both countries to critically review and improve extant, or develop new, competency-based management/leadership development programmes. The research findings lend no support to claims that national culture has a major impact on managerial and leadership practices, styles, and effectiveness.     

Use of a historical control group in a noninferiority trial assessing a new antibacterial treatment: A case study and discussion of practical implementation aspects

When recruitment into a clinical trial is limited due to rarity of the disease of interest, or when recruitment to the control arm is limited due to ethical reasons (eg, pediatric studies or important unmet medical need), exploiting historical controls to augment the prospectively collected database can be an attractive option. Statistical methods for combining historical data with randomized data, while accounting for the incompatibility between the two, have been recently proposed and remain an active field of research. The current literature is lacking a rigorous comparison between methods but also guidelines about their use in practice. In this paper, we compare the existing methods based on a confirmatory phase III study design exercise done for a new antibacterial therapy with a binary endpoint and a single historical dataset. A procedure to assess the relative performance of the different methods for borrowing information from historical control data is proposed, and practical questions related to the selection and implementation of methods are discussed. Based on our examination, we found that the methods have a comparable performance, but we recommend the robust mixture prior for its ease of implementation.     

Environmental justice in South Africa: tools and trade‐offs

Despite constitutional commitments to environmental justice in South Africa, evidence indicates that the poor and the natural environment continue to be marginalised in decision making. This paper examines the role of environmental assessment procedures, specifically Environmental Impact Assessments, in shaping outcomes at the local level to understand how injustices are perpetuated and maintained. Injustices are understood here by examining the relationship between power, knowledge and rationality, and the effects these have on including the public in decision‐making processes. In the revamping of environmental assessment regulations in South Africa, much attention has been paid to streamlining the process of assessment. However, this paper argues that environmentally just decisions cannot be made in a context where debates are centred on process. Instead, debates need to be redirected to qualities of outcomes, foregrounding the need for an approach grounded in questions of value. Recognising that the poor and the natural environment tend to systematically lose out in a context where environment is pitted against development, environmental assessment must be able to take into account the distributional consequences of decisions. Furthermore, the paper makes a case for the need to challenge the broader political context within which environmental assessments are conducted, as environmental assessments cannot replace broader strategic and policy debates. In the absence of this broader institutional challenge, political power will continue to work through decision‐making tools to perpetuate and maintain systems of injustice.     

Skewed Sex Ratios in India: “Physician, Heal Thyself”

Sex selection, a gender discrimination of the worst kind, is highly prevalent across all strata of Indian society. Physicians have a crucial role in this practice and implementation of the Indian Government’s Pre-Natal Diagnostic Techniques Act in 1996 to prevent the misuse of ultrasound techniques for the purpose of prenatal sex determination. Little is known about family preferences, let alone preferences among families of physicians. We investigated the sex ratios in 946 nuclear families with 1,624 children, for which either one or both parents were physicians. The overall child sex ratio was more skewed than the national average of 914. The conditional sex ratios decreased with increasing number of previous female births, and a previous birth of a daughter in the family was associated with a 38 % reduced likelihood of a subsequent female birth. The heavily skewed sex ratios in the families of physicians are indicative of a deeply rooted social malady that could pose a critical challenge in correcting the sex ratios in India.     

Use of baseline measurements in the two-period crossover design

It is proposed that baseline measurements be obtained prior to each period in a two-period crossover design. These measurements are used in a preliminary test for determining the validity of a test for treatment comparison and also for testing the hypothesis of equal treatment effects. The null hypothesis in this preliminary test consists of the following three hypotheses: that there is no difference in disease conditions prior to the two periods, no difference in residual effects of the drugs, and no treatment × period interaction.. A numerical example is given and the efficiencies of several methods are computed.     

Adoption of electronic-cigarette-free,hookah-free and American College Health Association recommended tobacco-free policies among a national sample of postsecondary educational institutions

Abstract

Objective: To examine the prevalence of various types of tobacco-free policies among a US national sample of postsecondary educational institutions (PEIs). Participants: A national sample of US PEIs (N?=?605) attended by the participants of the NEXT Generation Health Study. Methods: Tobacco policies of these PEIs were reviewed to determine if they were e-cigarette-free (yes/no), hookah-free (yes/no), and ACHA-recommended tobacco-free (yes/no) in June–December 2017. Logistic regression models were used to examine the relationships between institutional characteristics and tobacco policies. Results: Overall, 39.2, 26.0, and 20.0% of the sample adopted e-cigarette-free, hookah-free, and ACHA-recommended tobacco-free policies, respectively. Proprietary PEIs (vs. public) were less likely to have ACHA-recommended tobacco-free policies, while PEIs in the South and Midwest (vs. West) were more likely to have ACHA-recommended tobacco-free policies (p?<?0.05). Conclusions: Most sampled PEIs did not have ACHA-recommended tobacco-free polices. Subsequent research needs to investigate how ACHA-recommended tobacco policies influence tobacco use.