Model free audit methodology for bias evaluation of tumour progression in oncology

Many oncology studies incorporate a blinded independent central review (BICR) to make an assessment of the integrity of the primary endpoint, progression free survival. Recently, it has been suggested that, in order to assess the potential for bias amongst investigators, a BICR amongst only a sample of patients could be performed; if evidence of bias is detected, according to a predefined threshold, the BICR is then assessed in all patients, otherwise, it is concluded that the sample was sufficient to rule out meaningful levels of bias. In this paper, we present an approach that adapts a method originally created for defining futility bounds in group sequential designs. The hazard ratio ratio, the ratio of the hazard ratio (HR) for the treatment effect estimated from the BICR to the corresponding HR for the investigator assessments, is used as the metric to define bias. The approach is simple to implement and ensures a high probability that a substantial true bias will be detected. In the absence of bias, there is a high probability of accepting the accuracy of local evaluations based on the sample, in which case an expensive BICR of all patients is avoided. The properties of the approach are demonstrated by retrospective application to a completed Phase III trial in colorectal cancer. The same approach could easily be adapted for other disease settings, and for test statistics other than the hazard ratio. Copyright © 2015 John Wiley & Sons, Ltd.     

Bayesian Approaches to Nonparametric Estimation of Densities on the Unit Interval

This paper investigates nonparametric estimation of density on [0, 1]. The kernel estimator of density on [0, 1] has been found to be sensitive to both bandwidth and kernel. This paper proposes a unified Bayesian framework for choosing both the bandwidth and kernel function. In a simulation study, the Bayesian bandwidth estimator performed better than others, and kernel estimators were sensitive to the choice of the kernel and the shapes of the population densities on [0, 1]. The simulation and empirical results demonstrate that the methods proposed in this paper can improve the way the probability densities on [0, 1] are presently estimated.     

Asymptotic tests and monte carlo studies associated with the multiplicative interaction model

Several authors have proposed approximations to percentage points required for testing certain hypotheses associated with the multiplicative interaction model. Alternative approximations based on the asymptotic joint distribution of the characteristic roots of a noncentral Wishart matrix are proposed in this paper. The type I error rates of the resulting tests and the existing procedures are then compared using Monte Carlo methods.     

Formative research methods to understand patient and provider responses to heart attack symptoms

Formative research is often required for program planning, and for reducing uncertainty about generalizability of program effects. This article describes and justifies methods of formative research conducted for the REACT study (Rapid Early Action for Coronary Treatment), a multi-center collaborative randomized community trial aimed at reducing patient delay in seeking care for acute myocardial infarction (AMI). Formative research cast light on patient and community members’ decision-making process in seeking help for AMI, as well as barriers and facilitators of this process. Investigators at all five REACT Field Centers participated in the formative research. The process consisted of: (1) developing a common theoretical framework for the study intervention; (2) conducting a literature review and qualitative research to identify and address gaps in knowledge; and (3) developing a common protocol for the REACT study that accommodated the diversity of the target communities in terms of services, resources, history, and ethnicity. Analysis employed triangulation, defined as an explicit search for heterogeneous data sources to reduce uncertainty about forces at work and opportunities for intervention across settings and populations. Because the collection and interpretation of data went in stages, staff of several REACT Field Centers had independent input to the overall synthesis, then shared and revised the results. Advantages and limitations of this approach are discussed.     

Long- and short-term affective states in happiness: Model,paradigm and experimental evidence

The present paper evaluates relevant findings on long- and short-term affective states in subjective well-being and argues for a componential model that combines the two into the more general concept of happiness. Two age parameters, one for long-term and one for short-term affect are added to the simple model to account for age changes in happiness. Measures of long- and short-term affect are presented, as is a paradigm for separating the components. Support for the simple model is provided by an experimental investigation with 64 college students who were exposed to positive and/or negative mood induction. As expected, the induction had substantially greater effect on short- than on long-term affect measures, particularly the negative induction procedure. These findings are consistent with predictions. However, multiple age cohorts will have to be assessed within a longitudinal framework to obtain values for the age parameters.     

Associations among altruism, burnout dimensions, and organizational citizenship behaviour

Most studies of burnout have focused on lack of resources, prevalence of burnout, and negative outcomes. In contrast, this study examined the relationships among altruism, burnout and a positive outcome, namely, the engagement in organizational citizenship behaviour. Web questionnaires were distributed to employees in three professional organizations. The results from the 178 respondents indicated that altruism is related to organizational citizenship behaviour. Of the three dimensions of burnout, only reduced personal accomplishment was (negatively) associated with engagement in organizational citizenship behaviours. Implications of the results are discussed and directions for future research are offered.     

Nonparametric M-regression with free knot splines

Many problems of practical interest can be formulated as the nonparametric estimation of a certain function such as a regression function, logistic or other generalized regression function, density function, conditional density function, hazard function, or conditional hazard function. Extended linear modeling provides a convenient theoretical framework for using polynomial splines and their selected tensor products in such function estimation problems and especially for obtaining rates of convergence of the resulting estimates in a unified manner. For a long time the theoretical results were restricted to fixed knot splines and to log-likelihood functions that were twice continuously differentiable. Recently, Stone and Huang extended the theory to handle free knot splines. In the present paper, the theory is further extended to handle contexts in which the log-likelihood function may not be differentiable. Specifically, we establish rates of convergence for estimation based on free knot splines in the context of nonparametric regression corresponding to M-estimates, which includes least absolute deviations (LAD) regression, quantile regression, and robust regression as special cases.     

The Greater Ability of Graphical Versus Numerical Displays to Increase Risk Avoidance Involves a Common Mechanism

By displaying a risk reduction of 50% graphically rather than numerically, Stone, Yates, and Parker significantly increased professed risk-avoidant behavior. The current experiments replicated this effect at various risk ratios. Specifically, participants were willing to spend more money to reduce a risk when the risk information was displayed by asterisks rather than by numbers for risk-reduction ratios ranging from 3% to 97%. Transforming the amount participants were willing to spend to logarithms significantly improved a linear fit to the data, suggesting that participants convert this variable within the decision-making process. Moreover, a log-linear model affords an exceptional fit to both the graphical and numerical data, suggesting that a graphical presentation elicits the same decision-making mechanism as does the numerical display. In addition, the data also suggest that each person removed from harm is weighted more by some additional factor in the graphical compared to the numerical presentations.