Grading on the curve is a common practice in higher education. While there are many critics of the practice it still finds wide spread acceptance particularly in science classes. Advocates believe that in large classes student ability is likely to be normally distributed. If test scores are also normally distributed instructors and students tend…

Relationships among the noncentrality parameter for the "F" distribution, mean square between and within groups, and effect size are examined. (Author)

The accuracy of Kendall's chi square approximation (M. Kendall, 1962) to circular triad distributions was assessed by comparing estimated indices to enumerated values across upper and lower tails of cumulative proportions of circular triad distributions. In general, the approximation was found to be quite good, and its use is discussed. (SLD)

This paper presents two probabilistic models based on the logistic and the normal distribution for the analysis of dependencies in individual paired comparison judgments such as might occur in educational research. Three applications illustrate the approach. (SLD)

Two ideal-point probabilistic choice models from the external analysis of preferences are presented that allow for more flexible distributions of ideal-points. The first extends the probit model of W. Kamakura and R. Srivastava. The second is based on simplifying assumptions that lead to a multidimensional histogram of ideal-points. (SLD)

The frequencies of "m" independent "p-way" contingency tables are analyzed by a model that assumes that the ordinal category data in each of "m" groups are generated from a latent continuous multivariate normal distribution. The model permits analysis of several groups of individuals simultaneously. (TJH)

This paper makes the point that descriptive and inferential measures of nonnormality and graphic displays of the frequency distribution of important variables should be routine in research reporting. This point is particularly true for research involving measures with nonarbitrary metrics where the distribution shape is unaffected by measurement…

This paper discusses the issue of multiple testing and overall Type I error rates in contexts other than multiple comparisons of means. It demonstrates, using a 5 x 5 correlation matrix, the application of 5 recently developed modified Bonferroni procedures developed by the following authors: (1) Y. Hochberg (1988); (2) B. S. Holland and M. D.…

In many large-scale educational assessments it is of interest to compare the distribution of latent abilities of different subpopulations, and track these distributions over time to monitor educational progress. B. Junker, together with two colleagues, has developed a simple scheme, based on the proportion correct score, for smoothly approximating…

This paper considers the following questions: (1) what is the relationship between the method of paired comparisons and Rasch measurement theory? (2) what is the relationship between the method of paired comparisons and graph theory? and (3) what can graph theory contribute to the understanding of Rasch measurement theory? It is specifically shown…

The use of prevalence data is discussed to help find the best way to separate at-risk and not-at-risk groups. Implications of the data being distributed normally are also discussed and several examples, including one with a nonnormal distribution, are given. (Author/GK)

Glass's estimator of effect size, the sample mean difference divided by the sample standard deviation, is studied in the context of an explicit statistical model. The exact distribution of Glass's estimator is obtained and the estimator is shown to have a small sample bias. Alternatives are proposed and discussed. (Author/JKS)

An approximate statistical test is derived for the hypothesis that the intraclass reliability coefficients associated with two measurement procedures are equal. Control of Type 1 error is investigated by comparing empirical sampling distributions of the test statistic with its derived theoretical distribution. A numerical illustration is…

A systematic investigation of the Grice modeling scheme for response time (RT) clarifies fundamental notions about RT modeling. The analysis presented can be used to determine what in a certain RT model constitutes a set of empirically testable assumptions and what is merely an arbitrary choice of mathematical language. (SLD)

Previous research has demonstrated particular inadequacies in conventional methods used to identify outlier cases in bivariate regression models. Only through a combination of methods can one detect all of the deviant points potentially overinfluencing a regression model's parameters. This paper investigates whether a range of data points might…