Efficient designs for animal carcinogenicity experiments

In a typical carcinogenicity study, animals, usually rats or mice. are divided into a control and two to three dose groups of 50 or more by randomization. A chemical is administered at a constant daily dose rate for a major portion of the lifetime of the test animals, for example, two years. In general, such an experiment is expensive and time consuming In this paper, we propose an efficient design with reduced sample size and/or shortened study duration. An equal number of animals per dose group is considered in this study. A power study of the age-adjusted trend test, for the turnor incidence rate for single-sacrifice experiments proposed by Kodell et al. (Drug Information Journal, 1997) is conducted. A Monte Carlo simulation study is performed to compare the performance of the trend test for the standard design and various reduced designs. Based on the Kodell et al. test, the 21-month study duration with sample size 50 per group is recommended as the best, reduced design over the traditional 2-year study design with the same sample size.     

Distance-based outlier detection for high dimension,low sample size data

Despite the popularity of high dimension, low sample size data analysis, there has not been enough attention to the sample integrity issue, in particular, a possibility of outliers in the data. A new outlier detection procedure for data with much larger dimensionality than the sample size is presented. The proposed method is motivated by asymptotic properties of high-dimensional distance measures. Empirical studies suggest that high-dimensional outlier detection is more likely to suffer from a swamping effect rather than a masking effect, thus yields more false positives than false negatives. We compare the proposed approaches with existing methods using simulated data from various population settings. A real data example is presented with a consideration on the implication of found outliers.     

A mixed method approach to developing a multidimensional scale for gambling fallacy in the Korean context

This article offers an understanding of and reduces gaps in the existing literature regarding cognitive distortion (e.g. gambling fallacy) and problem gambling behaviour. The primary objective of this study is to develop a valid gambling fallacy scale for the South Korean population using qualitative and quantitative methods to thoroughly understand the underlying structure of erroneous beliefs towards gambling among recreational and problem gamblers. The study interviewed eight casino supervisors and dealers and conducted online (n = 1419 gamblers) and onsite surveys (n = 400 gamblers) in South Korea. The proposed scale satisfies reliability and numerous types of validity that provide evidence on the three distinctive underlying structures of gambling fallacy (i.e. a system to win, superstitions, and follow and blame) among the Korean population. This study carries substantial theoretical and practical implications that further assure its usability as a platform for developing scales in various cultural settings.     

Inference for comparing a multinomial distribution with a known standard

We propose a new type of stochastic ordering which imposes a monotone tendency in differences between one multinomial probability and a known standard one. An estimation procedure is proposed for the constrained maximum likelihood estimate, and then the asymptotic null distribution is derived for the likelihood ratio test statistic for testing equality of two multinomial distributions against the new stochastic ordering. An alternative test is also discussed based on Neyman modified minimum chi-square estimator. These tests are illustrated with a set of heart disease data.     

Rearticulating Black Mixed-Race in the Era of Globalization

Since the mid-2000s, the term multiculturalism has entered the Korean lexicon as migration has become more and more prevalent due to globalization. The cornerstone of this multicultural explosion was a 2006 visit by American football star Hines Ward, born to an African-American father and a Korean mother. As a black mixed-race sports celebrity, he suddenly became an emblematic media figure in the Korean televisual landscape, signifying a broader racial reconfiguration in Korean society. This media event – what I shall call ‘the Hines Ward moment’ – created and opened the discursive space for racial politics and multicultural issues in Korean society. Hence, this article aims to look at what this discursive explosion of multiculturalism and mixed-race means in the context of globalization. Reading the Hines Ward moment as a symbolic media text, the paper examines how the media discourse on Hines Ward articulates the issues of national identity and racial politics in contemporary Korean society. For analysis, newspaper articles, television programmes and television commercials that deal with the Hines Ward case are examined. By analyzing the modes of articulation of the Hines Ward moment, this study deconstructs the image of a ‘global, multicultural Korea’ shaped by the Korean media and examines the struggle for Koreanness in the televisual area of contemporary Korean media.     

Production quantity allocation for order fulfilment in the supply chain: a neural network based approach

In the current global business environment, it is very important to know how to allocate products from the producer to buyers (or distributors). If products are not appropriately distributed due to absence of an effective allocation policy, the producer and buyers cannot expect to increase customer satisfaction and financial profit. Sometimes some buyers can order more than the actual demand due to inappropriately forecasting customer orders. This is the big obstacle to the effective allocation of products. If the producer can become aware of buyers’ actual demands, it is possible to realise high-level order fulfilment through the effective allocation of products. In this study, new allocation policies are proposed considering buyers’ demands. The back propagation algorithm, one of the learning algorithms in neural network theory, is used to recognise actual demands from the previous buyers’ orders. After excluding surplus demands included in buyers’ demands, products are allocated to buyers according to one of the existing allocation policies depending on the company's decision. In the numerical examples, new allocation policies reducing buyers’ surplus demands outperform previous allocation policies with respect to average amount of backorder.     

Combinatorial Voting

We study elections that simultaneously decide multiple issues, where voters have independent private values over bundles of issues. The innovation is in considering nonseparable preferences, where issues may be complements or substitutes. Voters face a political exposure problem: the optimal vote for a particular issue will depend on the resolution of the other issues. Moreover, the probabilities that the other issues will pass should be conditioned on being pivotal. We prove that equilibrium exists when distributions over values have full support or when issues are complements. We then study large elections with two issues. There exists a nonempty open set of distributions where the probability of either issue passing fails to converge to either 1 or 0 for all limit equilibria. Thus, the outcomes of large elections are not generically predictable with independent private values, despite the fact that there is no aggregate uncertainty regarding fundamentals. While the Condorcet winner is not necessarily the outcome of a multi‐issue election, we provide sufficient conditions that guarantee the implementation of the Condorcet winner.     

Investing in a Shared Supplier in a Competitive Market: Stochastic Capacity Case

When firms invest in a shared supplier, one key concern is whether the invested capacity will be used for a competitor. In practice, this concern is addressed by restricting the use of the capacity. We consider what happens when two competing firms invest in a shared supplier. We consider two scenarios that differ in how capacity is used: exclusive capacity and first‐priority capacity. We model firms' investment and production decisions, and analyze the equilibrium outcomes in terms of the number of investing firms and capacity levels for each scenario; realized capacity is a stochastic function of investment levels. We also identify conditions under which the spillover effect occurs, where one firm taps into the other firm's invested capacity. Although the spillover supposedly intensifies competition, it actually discourages firms' investment. We also characterize the firms' and supplier's preference about the capacity type. While the non‐investing firm always prefers spillovers from the first‐priority capacity, the investing firm does not always want to shut off the other firm's access to its leftover capacity, especially when allowing spillover induces the other firm not to invest. The supplier's preference depends on the trade‐off between over‐investment and flexibility.     

Using ranked set sampling with binary outcomes in cluster randomized designs

We study the use of ranked set sampling (RSS) with binary outcomes in cluster-randomized designs (CRDs), where a generalized linear mixed model (GLMM) is used to model the hierarchical data structure involved. Under the GLMM-based framework, we propose three different approaches to estimate the treatment effect, including the nonparametric (NP), maximum likelihood (ML) and pseudo likelihood (PL) estimators. We investigate their asymptotic properties and examine their finite-sample performance via simulation. Based on these three RSS estimators, we further develop procedures for testing the existence of the treatment effect. We examine the power and size of our proposed RSS tests and compare them with existing tests based on simple random sampling (SRS). All the proposed RSS estimation and test methods are illustrated with two data examples, one for rare events and the other for non-extreme events. Throughout our investigations, we also consider the possible effect of imperfect ranking. Among the proposed methods, we provide recommendations on whether to use RSS rather than SRS with binary outcomes in CRDs and, if yes, when to use which RSS method. The Canadian Journal of Statistics 48: 342–365; 2020 © 2019 Statistical Society of Canada