Sample Size Determination for Categorical Responses

Abstract:  Procedures are reviewed and recommendations made for the choice of the size of a sample to estimate the characteristics (sometimes known as parameters) of a population consisting of discrete items which may belong to one and only one of a number of categories with examples drawn from forensic science. Four sampling procedures are described for binary responses, where the number of possible categories is only two, e.g., licit or illicit pills. One is based on priors informed from historical data. The other three are sequential. The first of these is a sequential probability ratio test with a stopping rule derived by controlling the probabilities of type 1 and type 2 errors. The second is a sequential variation of a procedure based on the predictive distribution of the data yet to be inspected and the distribution of the data that have been inspected, with a stopping rule determined by a prespecified threshold on the probability of a wrong decision. The third is a two-sided sequential criterion which stops sampling when one of two competitive hypotheses has a probability of being accepted which is larger than another prespecified threshold. The fifth procedure extends the ideas developed for binary responses to multinomial responses where the number of possible categories (e.g., types of drug or types of glass) may be more than two. The procedure is sequential and recommends stopping when the joint probability interval or ellipsoid for the estimates of the proportions is less than a given threshold in size. For trinomial data this last procedure is illustrated with a ternary diagram with an ellipse formed around the sample proportions. There is a straightforward generalization of this approach to multinomial populations with more than three categories. A conclusion provides recommendations for sampling procedures in various contexts.     

Banking regulation,regulatory capture and inequality

Public Choice - Regulation of the banking and finance industry may lead to a more equal distribution of income if regulators pursue goals in the public interest. Alternatively, the economic theory...     

Government Promotion of Corporate Social Responsibility: Evidence from the EU Eco‐Management and Audit Scheme

Governments play an active role in promoting corporate social responsibility and specifically environmental management system (EMS) programs, but few studies have examined the impact of such support on the decision of businesses to adopt EMS programs. We ask two questions in this paper: how does government support for EMS programs affect adoption of such programs? Second, what effect does this government support have on the pace of adoption of such programs? The answer to the first question can reveal how effective government programs are in boosting membership in EMS programs. The answer to the second reveals to what extent businesses within EU member states are converging upon particular EMS standards. We examine these questions in the context of the European Union’s Eco‐Management and Audit Scheme (EMAS), 2010–2014. There is significant variation in government support of EMAS across the EU and at the same time, EMAS competes for business attention with the more established ISO 14001. Our quantitative and qualitative analyses therefore reveal the effectiveness of government programs in boosting adoption, but also to the extent to which such programs cause convergence upon EMAS in the face of a competing standard such as ISO 14001.     

Hybrid Strategies: The American Experience

The United States has never followed only one grand strategy at a time. In this article, I develop the concept of “hybrid” grand strategies—strategies that vary by time and place, and combine the advantages (or disadvantages) of pure strategic archetypes such as containment, integration, regime change, bargaining, or non-intervention. I argue that hybrid strategies have been ubiquitous in American history, varying more by emphasis and degree than by absolute contrast. Moreover, U.S. hybrid strategies have often succeeded in accomplishing their major goals.     

Methodologies of election forecasting: Calling the 2010 UK “hung parliament”

Election forecasting has experienced considerable growth as a subfield within political science. Research work on United Kingdom elections has been cutting edge here. The recent 2010 general election afforded the opportunity for a trial of different forecasting methodologies. These efforts are showcased in this volume, and include standard, and not-so-standard, statistical models. Overall, these models perform well, foreseeing the unprecedented outcome of a “hung parliament”, as most pollsters and pundits did not. Moreover, they achieved this accuracy with forecasts well in advance of the election itself.     

The decomposition of rabbit carcasses and associated necrophagous Diptera in Kuwait

Rabbit carcasses were used to compare rates of decomposition and associated assemblages of Diptera at four discernable habitat types in Kuwait; a country of a region with a paucity of such reference data. Carcasses in an urban habitat showed faster decomposition (as measured by percentage weight loss) than in agricultural, coastal or desert habitats, even with accumulated degree days (ADD) as the explanatory variable (t=2.73, df=34, p=0.010) to compensate for temperature differences. Taxa of Diptera at the four habitats became more similar as decomposition progressed, suggesting such differences between habitats were not marked. The occurrence of Chrysomyia megacephala and Lucilia sericata had not previously been recorded in Kuwait.