On the use of extreme value tail modeling for generalized pairwise comparisons with censored outcomes

In randomized clinical trials, methods of pairwise comparisons such as the ‘Net Benefit’ or the ‘win ratio’ have recently gained much attention when interests lies in assessing the effect of a treatment as compared to a standard of care. Among other advantages, these methods are usually praised for delivering a treatment measure that can easily handle multiple outcomes of different nature, while keeping a meaningful interpretation for patients and clinicians. For time-to-event outcomes, a recent suggestion emerged in the literature for estimating these treatment measures by providing a natural handling of censored outcomes. However, this estimation procedure may lead to biased estimates when tails of survival functions cannot be reliably estimated using Kaplan–Meier estimators. The problem then extrapolates to the other outcomes incorporated in the pairwise comparison construction. In this work, we suggest to extend the procedure by the consideration of a hybrid survival function estimator that relies on an extreme value tail model through the Generalized Pareto distribution. We provide an estimator of treatment effect measures that notably improves on bias and remains easily apprehended for practical implementation. This is illustrated in an extensive simulation study as well as in an actual trial of a new cancer immunotherapy.     

Testing the proportional odds assumption in multiply imputed ordinal longitudinal data

A popular choice when analyzing ordinal data is to consider the cumulative proportional odds model to relate the marginal probabilities of the ordinal outcome to a set of covariates. However, application of this model relies on the condition of identical cumulative odds ratios across the cut-offs of the ordinal outcome; the well-known proportional odds assumption. This paper focuses on the assessment of this assumption while accounting for repeated and missing data. In this respect, we develop a statistical method built on multiple imputation (MI) based on generalized estimating equations that allows to test the proportionality assumption under the missing at random setting. The performance of the proposed method is evaluated for two MI algorithms for incomplete longitudinal ordinal data. The impact of both MI methods is compared with respect to the type I error rate and the power for situations covering various numbers of categories of the ordinal outcome, sample sizes, rates of missingness, well-balanced and skewed data. The comparison of both MI methods with the complete-case analysis is also provided. We illustrate the use of the proposed methods on a quality of life data from a cancer clinical trial.     

Quantitative Microbial Risk Assessment of Cryptosporidiosis and Giardiasis from Very Small Private Water Supplies

This article reports a quantitative microbial risk assessment of the risk of Giardia and Cryptosporidium in very small private water supplies. Both pathogens have been implicated in causing outbreaks of waterborne disease associated with such supplies, though the risk of endemic disease is not known. For exposure assessments, we used existing data to derive regression equations describing the relationships between the concentration of these pathogens and Escherichia coli in private water supplies. Pathogen concentrations were then estimated using national surveillance data of E. coli in private water supplies in England and France. The estimated risk of infection was very high with the median annual risk being of the order of 25–28% for Cryptosporidium and 0.4% to 0.7% for Giardia, though, in the poorer quality supplies the risk could be much higher. These risks are substantially greater than for public water supplies and well above the risk considered tolerable. The observation that observed infection rates are generally much lower may indicate increased immunity in people regularly consuming water from private supplies. However, this increased immunity is presumed to derive from increased disease risk in young children, the group most at risk from severe disease.     

CIVIL SOCIETY AND THE STATE: THE INTERPLAY BETWEEN COOPERATION AND MINIMUM WAGE REGULATION

In a cross‐section of countries, state regulation of labor markets is negatively correlated with the quality of labor relations. In this paper, we argue that these facts reflect different ways of regulating labor markets, either through the state or through the civil society, depending on the degree of cooperation in the economy. We rationalize these facts with a model of learning of the quality of labor relations. Distrustful labor relations lead to low unionization and high demand for direct state regulation of wages. In turn, state regulation crowds out the possibility for workers to experiment negotiation and learn about the potential cooperative nature of labor relations. This crowding out effect can give rise to multiple equilibria: a “good” equilibrium characterized by cooperative labor relations and high union density, leading to low state regulation; and a “bad” equilibrium, characterized by distrustful labor relations, low union density, and strong state regulation of the minimum wage.     

Comparison of two methods of measuring physical activity in South African older adults

The aim of this study was to assess the validity and reliability of the Yale Physical Activity Survey (YPAS) and the short version of the International Physical Activity Questionnaire (IPAQ) in older South African adults. The YPAS includes measures of weekly energy expenditure (EE) for housework, yard work, caregiving, exercise, and recreation. The IPAQ measures total time and EE during vigorous and moderate activity, walking, and sitting. The instruments were administered twice for test-retest reliability (men, n = 52, 68 +/- 5.4 years, and women, n = 70, 66 +/- 5.8 years). Data for criterion validity were obtained from accelerometers. YPAS reliability ranged from r = .44 to.80 for men and r = .59 to .99 for women (p < .0001). IPAQ reliability was lower for men (r = .29 to .76) than for women (r = .46 to .77). Criterion validity of the YPAS was .31 to .54 for men and .26 to .29 for women. The YPAS and short IPAQ had comparable results for reliability and criterion validity.     

Multiple Book Review: Four Perspectives on Human Natures: Genes,Cultures, and the Human Prospect. Paul R. Ehrlich. Washington,DC: Island Press, 2000, 531 pp.

Population and Environment -     

Avoiding “regulatory mismatch in regulating workplace ergonomics: The case for an informational approach

Conclusion My basic point is simple: OSHA, in its zeal to ensure safer workplaces, should remember that its primary task as a regulatory agency is to correct market failures and should tailor its regulatory solutions to respond to market failures efficiently. The most efficient solution to a market failure will generally be the least restrictive regulatory alternative, for such an alternative maximizes the ability of individual actors to engage in wealthcreating private ordering. With respect to inadequate ergonomic protections in the workplace, the culprit market failure is not a negative externality but is — if there truly is a market failure — systematic informational inadequacies on the part of employees (about ergonomic risks) and employers (about available precautions). The most narrowly tailored regulatory solution, and therefore the one most likely to preserve the wealth-creation benefits of private ordering, would focus on providing the systematically under-produced information to the relevant actors.     

Le traitement syndical du racisme et de l'insécurité dans une entreprise de transports urbains

On-the-job racism is studied in the case of a public transportation firm that has to cope with insecurity in an urban area. In this company, the labor union has related security and racism in order to definitively integrate young persons hired to do “mediation work”. Eliminating this work from the list of jobs has had two positive effects; it avoids the risk of an “ethnic professionalization” and grants legitimacy to the relational know-how linked to the origins of young wage-earners. The option of labor union members in the firm did curb the escalation of conflicts between transportation personnel and young people in housing projects.     

Two-Sample Statistics for Testing the Equality of Survival Functions Against Improper Semi-parametric Accelerated Failure Time Alternatives: An Application to the Analysis of a Breast Cancer Clinical Trial

This paper presents two-sample statistics suited for testing equality of survival functions against improper semi-parametric accelerated failure time alternatives. These tests are designed for comparing either the short- or the long-term effect of a prognostic factor, or both. These statistics are obtained as partial likelihood score statistics from a time-dependent Cox model. As a consequence, the proposed tests can be very easily implemented using widely available software. A breast cancer clinical trial is presented as an example to demonstrate the utility of the proposed tests.     

Statistical Estimation for a Class of Self‐Regulating Processes

Self‐regulating processes are stochastic processes whose local regularity, as measured by the pointwise Hölder exponent, is a function of amplitude. They seem to provide relevant models for various signals arising for example in geophysics or biomedicine. We propose in this work an estimator of the self‐regulating function (that is, the function relating amplitude and Hölder regularity) of the self‐regulating midpoint displacement process and study some of its properties. We prove that it is almost surely convergent and obtain a central limit theorem. Numerical simulations show that the estimator behaves well in practice.