Relativism is an inevitable consequence of our interpretive mode of being in the world. This is so for both our daily lives and our professional lives. What does not overly concern us at the former level should likewise not concern us at the latter level. (Author/BJV)

The data collected in higher education research are not always quantitative or continuous. Statistical methods using the log-linear model provide the institutional researcher with a powerful set of tools for addressing research questions when data are categorical. (Author/MSE)

Path analysis and linear structural relations (LISREL) provide the institutional researcher with some extremely powerful statistical tools. However, they must be applied and interpreted carefully with a full understanding of their limitations and the statistical assumptions on which they are based. (Author)

Examined factor structure of Career Decision Scale (CDS), comparing findings of seven factor analytic studies. Conducted new factor analytic study of CDS designed to avoid methodological problems of earlier studies, using 698 secondary school students as subjects. Results suggest "Simple" model of CDS factor structure could be derived…

Discusses use of computer simulation as an archeological tool for research and teaching involving the remains of prehistoric game animals to aid in understanding effects of various strategies of prehistoric hunters on populations of game animals. A simulation involving possible vicuna hunting strategies is described. (MBR)

Maintains that usual method of analyzing student evaluation of teaching (SET) data is inappropriate. Shows results of both ordinary least squares (OLS) and multinominal logit data analysis approaches on 6,872 student evaluation of economics faculty at University of California, Santa Barbara during the 1983-84 academic year. Results show…

Provides a classroom demonstration designed to test an astrological hypothesis and help teach introductory psychology students about research design and data interpretation. Illustrates differences between science and nonscience, the role of theory in developing and testing hypotheses, making comparisons among groups, probability and statistical…

The Bayesian inferential process is modified for use in an aggregate meta-analytic evaluation. Compared with the average effect size meta-analytic approach, the Bayesian approach was more sensitive, more consistent and more powerful. This approach is recommended when primary data are not available and when all evaluations involve comparisons of…

A glance at any newspaper shows that graphs play an important part in presenting data to the public. It appears self-evident that children need to develop "graphical literacy" as part of their mathematics education. As part of a series of mathematically orientated science activities in the Practical Mechanics in Primary Mathematics project, 102…

This report examines how Juvenile Detention Alternatives Initiative (JDAI) sites used data to plan reforms and assess reform success, noting where and how they gathered data. Chapter 1, "The Need for Data," discusses: assessing data utilization, using data to enhance communication, and using this report to support reform. Chapter 2,…

Discusses and compares the meaning of epistemic uses of modals. Demonstrates that the relation between them is not as simple as has been frequently suggested. The article bases its observations on the data from a corpus of parallel French and English texts, pointing out that such a corpus can open new avenues for investigation of an old topic. (18…

The seven chapters of this special issue explore problems in how to better understand the reasoning process that is used to establish evaluative conclusions. The many unanswered questions about reasoning should stimulate further investigation of the meaning of sound evaluative reasoning. (SLD)

Assessment is described from the perspective of counselor inferential judgment. The problem with the conceptualization of assessment as a list of questions or measure is the possibility of getting stuck in the content of assessment. Types of cognitive bias and ways to avoid inferential error are discussed. (LKS)

This paper compares the results of National Center for Education Statistics (NCES) and the Carnegie surveys of postsecondary faculty and notes the differently constructed samples, the different response rates, and different weighting schemes in analysis and interpretation. Inconsistencies in the surveys' results are identified and methodological…

The degree of agreement between two raters rating several objects for a single characteristic can be expressed through an association coefficient, such as the Pearson product-moment correlation. How to select an appropriate association coefficient, and the desirable properties and uses of a class of such coefficients--the Euclidean…