Reviews of Books and Teaching Materials

ActivStats 2.0.: Paul Velleman. Reading, MA: Addison-Wesley, 1998, CD-ROM, $44.25, ISBN: 0-201-31068-6.

The Active Practice of Statistics.: David S. Moore. New York: W. H. Freeman & Co., 1997, xv + 352 pp., $49.95, ISBN: ISBN 0-7167-3140-1. Reviewed by Jon Maatta

Introduction to Statistical Reasoning.: Gary Smith. Boston: McGraw-Hill, 1998, xviii + 654 pp., $46.00, ISBN: 0-07-059276-4. Reviewed by Robert W. Hayden

Modern Applied Statistics with S-Plus (2nd ed.).: William N. Venables and Brian D. Ripley. New York: Springer-Verlag, 1997, xvii + 548 pp., $59.95, ISBN: 0-387-98214-0. Reviewed by Karen Kafadar James R. Koehler

A Course in Mathematical Statistics (2nd ed.): George C. Roussas. San Diego: Academic Press, 1997, xx + 572 pp., $59.95, ISBN: 0125993153. Reviewed by David W. Macky     

Internet Use Among College Students: An Exploratory Study

Abstract

The author and associates surveyed 1,300 college students in classrooms at eight academic institutions to identify how the students' use of the Internet has affected their social or academic lives. Although the typical Internet-using student uses the Internet for 100 minutes per day, a small group of students use the Internet to a degree that interferes with other aspects of their lives. Most of them are men and are found among the hard science academic majors. Some ideas for dealing with this problem are suggested.     

GLOBALIZATION AND TRINIDAD CARNIVAL: DIASPORA,HYBRIDITY AND IDENTITY IN GLOBAL CULTURE

This article is premised on the view that culturally, the periphery is greatly influenced by the society of the centre, but the reverse is also the case. This is a case study of the impact and implications for global culture of periphery-to-centre cultural flows. It is argued that the Trinidad carnival and the overseas Caribbean carnivals (e.g. Notting Hill, London; Caribana, Toronto; Labour Day, New York) are products of and responses to the processes of globalization as wellas transcultural and transnational formations. Carnival is theorized as a hybrid site for the ritual negotiation of cultural identity and practice by the Caribbean diaspora.     

Separability tests for high-dimensional,low-sample size multivariate repeated measures data

Longitudinal imaging studies have moved to the forefront of medical research due to their ability to characterize spatio-temporal features of biological structures across the lifespan. Valid inference in longitudinal imaging requires enough flexibility of the covariance model to allow reasonable fidelity to the true pattern. On the other hand, the existence of computable estimates demands a parsimonious parameterization of the covariance structure. Separable (Kronecker product) covariance models provide one such parameterization in which the spatial and temporal covariances are modeled separately. However, evaluating the validity of this parameterization in high dimensions remains a challenge. Here we provide a scientifically informed approach to assessing the adequacy of separable (Kronecker product) covariance models when the number of observations is large relative to the number of independent sampling units (sample size). We address both the general case, in which unstructured matrices are considered for each covariance model, and the structured case, which assumes a particular structure for each model. For the structured case, we focus on the situation where the within-subject correlation is believed to decrease exponentially in time and space as is common in longitudinal imaging studies. However, the provided framework equally applies to all covariance patterns used within the more general multivariate repeated measures context. Our approach provides useful guidance for high dimension, low-sample size data that preclude using standard likelihood-based tests. Longitudinal medical imaging data of caudate morphology in schizophrenia illustrate the approaches appeal.     

A Comparison of Two Tests for Equality of Two Proportions

Two procedures for testing equality of two proportions are compared in terms of asymptotic efficiency. The comparison favors use of a statistic equivalent to Goodman's Y ² over the usual X ² statistic in some cases including that of equal sample sizes. Numerical comparisons indicate that the asymptotic results have some relevance for moderate sample sizes.     

Combining strength and uncertainty for preferences in the graph model for conflict resolution with multiple decision makers

A hybrid preference framework is proposed for strategic conflict analysis to integrate preference strength and preference uncertainty into the paradigm of the graph model for conflict resolution (GMCR) under multiple decision makers. This structure offers decision makers a more flexible mechanism for preference expression, which can include strong or mild preference of one state or scenario over another, as well as equal preference. In addition, preference between two states can be uncertain. The result is a preference framework that is more general than existing models which consider preference strength and preference uncertainty separately. Within the hybrid preference structure, four kinds of stability are defined as solution concepts and a post-stability analysis, called status quo analysis, which can be used to track the evolution of a given conflict. Algorithms are provided for implementing the key inputs of stability analysis and status quo analysis within the extended preference structure. The new stability concepts under the hybrid preference structure can be used to model complex strategic conflicts arising in practical applications, and can provide new insights for the conflicts. The method is illustrated using the conflict over proposed bulk water exports from Lake Gisborne in Newfoundland, Canada.