Issue: 2004 Volume 42

(4) Statistics Courses in the Business Curriculum: The Relationship Between Text and Context

Deborah J. Gougeon
University of Scranton


Focusing on statistics courses in the business curriculum, this paper examines the data on topical coverage in thirty-one college Business Statistics textbooks. While there is general agreement among business educators that the development of quantitative skills, especially in statistics, should be a core requirement in all business curricula, there is very little that is certain about what the specific content of such courses should be. Because there is little agreement on the specific content of Business Statistics courses, it is often difficult for teachers to find a text that actually “fits” in terms of topics taught, and that is also pedagogically satisfying in terms of organization, numbers, and types of problems, levels of difficulty, etc. A presentation and analysis of the results of this topical survey are provided, along with suggestions for future research.


Gougeon, D. J. (2004). Statistics courses in the business curriculum: The relationship between text and context. Florida Journal of Educational Research42(4), 71-89.

Download File: Gougeon.421.pdf (1042 downloads )

(3) The Effects of Integrated Interdisciplinary Classroom Instruction on a School-Based Smoking Program

Greg Jordan
University of South Florida


This study examines the implementation and effectiveness of a pilot interdisciplinary tobacco awareness/education and decision-making skills program for public and private middle grade students (grades 5-8) mandated for sixth graders for the school year 1999/2000 by the Florida Department of Health Office of Tobacco Control. This program was designed to be implemented by regular classroom teachers in a variety of subject specialties, and so incorporated an interdisciplinary, integrated approach to learning as well as theories of cognitive flexibility and situated learning. Students’ knowledge, attitudes, and decision-making skills about tobacco use were examined both before and after involvement in the program in order to determine the amount of impact the program made on students.


Jordan, G. (2004). The effects of integrated interdisciplinary classroom instruction on a school-based smoking program. Florida Journal of Educational Research42(1), 41-70.

Download File: Jordan.421.pdf (3415 downloads )

(2) A Comparison of First and Second Generation Multivariate Analyses: Canonical Correlation Analysis and Structural Equation Modeling

A. J. Guarino
Auburn University


This study illustrates that Structural Equation Modeling (SEM) provides a more accurate representation of the latent variables as assessed by the structure coefficients than Canonical Correlation Analysis (CCA). A heuristic data set of five independent variables representing the Piagetian tasks measured by The Inventory of Piaget’s Developmental Tasks (IPDT) and three dependent variables assessed by the Alabama Basic Competency Tests (BCT) were analyzed with both statistical methods. Although the relationship between IPDT and BCT was invariant, the corresponding latent variable structures differed for the two methods.


Guarino, A. J. (2004). A comparison of first and second generation multivariate analyses: Canonical correlation analysis and structural equation modeling. Florida Journal of Educational Research42(1), 22-40.

Download File: Guarino.421.pdf (1178 downloads )

(1) A Cautionary Note on Shrinkage Estimates of School and Teacher Effects

Richard L. Tate
Florida State University


Increasing use of “shrinkage” estimates of school and teacher effects on student achievement in educational accountability programs has been associated with arguments that multilevel models are more appropriate for the hierarchical structure of the school situation. Such estimates are usually presented as statistically optimal in that they minimize the mean square error of the estimates, a desirable property achieved by intentional introduction of a bias into the effect estimate. There is little evidence that those designing accountability programs are aware of the possible problematic nature of the differential bias associated with shrinkage estimates. In particular, intuitive rankings of school or teacher effects that are based on observed achievement means can under some circumstances be dramatically changed when shrinkage estimates are used. It is argued that all stakeholders in educational accountability programs should be aware of and agree to this feature of a system based on shrinkage estimates.


Tate, R. L. (2004). A cautionary note on shrinkage estimates of school and teacher effects. Florida Journal of Educational Research42(1), 1-21.

Download File: Tate.421.pdf (4446 downloads )