Wilcoxon–Mann–Whitney test for stratified samples and Efron's paradox dice

Two-treatment multi-center clinical trials are the most common type of clinical trials in practice. The aim of this paper is to discuss a curious property of certain standard nonparametric procedures used in the analysis of such clinical trials. Different analyses of a simulated data example are presented, which lead to contrasting and surprising results. The source of the potentially misleading outcome is then explored while relating the simulated data with the concept of Efron's paradox dice and the notion of nontransitivity. With the root of the problem established, an alternate nonparametric method from the literature is shown to address the problem. Finally, pointing out an interpretational concern of using the alternate procedure, a modification to this procedure is also suggested and corresponding theoretical results are presented.     

WOMEN'S WORK:

We use in-depth interviews, participant observation, and document analysis to examine women's involvement in the Gulf War Illness movement. We find that women's cumulative grievances of health concerns, financial hardships, and emotional problems opened them to movement recruitment as they surfed the Internet for information and support. The movement's division of labor was influenced not by gender but by health status. Women used the Internet to provide medical information and emotional support to geographically dispersed veterans. Activism transformed women activists by endowing them with a sense of empowerment and a somewhat broadened concern for social justice. Although their transformations disposed the women to become active on related issues, it did not extend to concerns about gender discrimination. We suggest that the next research step is to investigate gender differences in movement processes by surveying activists across a variety of movements to test propositions and to identify the characteristics of other social contexts that structurally instigate a departure from traditional gender roles.     

Racial Group Comparisons of Conceptualizations of Rap Music Constructs: A Cross-racial Validity Study of the Rap Music Attitude and Perception Scale

Interpretations and perceptions of the effects and content of rap music lyrics have been given considerable attention in the literature in recent years, yet few assessment tools have been developed that can produce reliable and valid inferences about these views. One exception is the Rap-music Attitude and Perception (RAP) Scale. This study examined the cross-racial effects on attitudes toward and perceptions of rap music using a sample of 1,254 college students. A cross-sectional survey design was used to gather these data. Three specific hypotheses were tested and were supported or partially supported. Alpha reliabilities for the full scale and for each of the three sub-scales were good for black and white students separately. Criterion validity for these groups was also good. Finally, tests of factorial equivalence suggested that the factor structure of the RAP was equivalent across racial groups. The RAP is a tool with strong psychometric properties and can be used by practitioners and researchers working with black and white subgroups. Directions for future research on the utility of the RAP are forwarded.     

Financial Intermediation Modernization in Countries with Transition Economy

During the modern phase of economic reforms directed at the establishment of market economy, many countries with transition economies face the challenge of solving the issue of formation and rational usage of internal sources of financing the real sector of the economy, as well as attracting considerable volume of direct foreign investment. In general, financial market imperfections hold back innovation and growth, and that public policy can complement financial markets. Therefore, the most relevant issue at the present time is the formation of attendant and complex supervision institutions, as well as an exigency of innovative economy governance as mainframe principles for further banking system elaboration and financial sector development in general. We have taken Armenia as a case study for transition economy as far as Armenia is currently in the stage of capital market development through integration into international financial markets.      

Engaging with Comparative Risk Appraisals: Public Views on Policy Priorities for Environmental Risk Governance

Communicating the rationale for allocating resources to manage policy priorities and their risks is challenging. Here, we demonstrate that environmental risks have diverse attributes and locales in their effects that may drive disproportionate responses among citizens. When 2,065 survey participants deployed summary information and their own understanding to assess 12 policy‐level environmental risks singularly, their assessment differed from a prior expert assessment. However, participants provided rankings similar to those of experts when these same 12 risks were considered as a group, allowing comparison between the different risks. Following this, when individuals were shown the prior expert assessment of this portfolio, they expressed a moderate level of confidence with the combined expert analysis. These are important findings for the comprehension of policy risks that may be subject to augmentation by climate change, their representation alongside other threats within national risk assessments, and interpretations of agency for public risk management by citizens and others.     

Evaluating Probabilistic Forecasts with Bayesian Signal Detection Models

We propose the use of signal detection theory (SDT) to evaluate the performance of both probabilistic forecasting systems and individual forecasters. The main advantage of SDT is that it provides a principled way to distinguish the response from system diagnosticity, which is defined as the ability to distinguish events that occur from those that do not. There are two challenges in applying SDT to probabilistic forecasts. First, the SDT model must handle judged probabilities rather than the conventional binary decisions. Second, the model must be able to operate in the presence of sparse data generated within the context of human forecasting systems. Our approach is to specify a model of how individual forecasts are generated from underlying representations and use Bayesian inference to estimate the underlying latent parameters. Given our estimate of the underlying representations, features of the classic SDT model, such as the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC), follow immediately. We show how our approach allows ROC curves and AUCs to be applied to individuals within a group of forecasters, estimated as a function of time, and extended to measure differences in forecastability across different domains. Among the advantages of this method is that it depends only on the ordinal properties of the probabilistic forecasts. We conclude with a brief discussion of how this approach might facilitate decision making.     

Evaluating correlated outcomes and sources of new information

This paper considers the difficulties associated with evaluating the expected value of additional information when the outcomes of various decision alternatives may be correlated. Such correlation is explained in terms of dependence of outcomes on common exogenous factors and it is argued that decisions regarding what, if any, additional information to collect should take such dependencies into account. A model-based ‘fixed-parameter’ approach to evaluating EVPI in such a context is developed and compared to the traditional ‘fixed-correlation’ approach. The results suggest that different assumptions about the issue of correlation can produce different, sometimes contradictory, conclusions about the expected value of additional information and bence, should be explicitly stated as part of any pre-posterior analysis. A hybrid model encompassing both approaches and rooted in the theory of psychology of inference is then proposed and illustrated.