A brief historical background of discriminant analysis is given, with a description of the variety of roles that discriminant analysis can perform. Focus is on the classification role of discriminant analysis and how it can be performed by using Fisher's classification functions or the canonical discriminant functions. A small hypothetical data…

During the last decade the use of Bayesian statistical method has become quite prevalent in the educational community. Yet, like most statistical techniques, little has been written concerning the application of these methods to the classroom setting. The purpose of this paper is to help correct such a deficiency in the literature by developing a…

An important problem in psychological test theory is the development of a sound method for determining whether a test which purports to measure the level of a certain ability is, in reality, significantly contaminated by one or more other abilities displayed by persons taking the test. Because of the large number of private and governmental…

This article presents two criterion-referenced grading models (a binomial grading model and an arcsine grading model), and shows how they can be applied in classrooms. In both cases, grades can be assigned on the basis of a criterion-referenced test with systematic control of the possible errors of misclassification (Author/BW)

This paper illustrates an application of Efron's bootstrap to the repeated measures design. While this approach does not require parametric assumptions, it does utilize distributional information in the sample. By appropriately resampling from study data, the bootstrap may determine accurate sampling distributions for estimators, effects, or…

This response to the Baglin paper (1986) points out the fallacy in inferring that inappropriate scaling procedures cause apparent discrepancies between medians and means and between means calculated using different units. (LMO)

Presents Price's law, which states that half of the literature on a subject will be contributed by the square root of total number of authors publishing in that area, and assesses it against empirical evidence and simulated productivity distributions. The discussion covers this law's relation to Lotka's law and its empirical validity. (Author/CLB)

Presents a model and experimental results of a new one-phase technique for compression text files that is a modification of the Ziv and Lempel compression scheme. The description includes the use of a subword dictionary that is periodically reorganized based on information theory and structural linguistics principles. (29 references) (Author/CLB)

This study was concerned with the effects of reliability of observations, sample size, magnitudes of treatment effects, and the shape of the sampled population on the relative power of the paired samples rank transform statistic and Wilcoxon's signed ranks statistic. (Author/LMO)

The use of semiparametric models may require incorporating additional functions which do not vary across distributions and may require expressing the models in terms of the joint distribution of response class and response time. (Author/LMO)

Analysis of works in American literature from the Modern Language Association International Bibliography (1981) in regard to form, class of materials, language, subject, and age found more references to books than journal articles, and age dispersion was broad. Comparisons are made to other similar studies in sciences and humanities. (Author/EM)

Three exact probability tests, counterparts of t tests for single sample, independent samples, and dependent samples, are described for data obtained from ratings on "m" scales by a single rater or on a single scale by "n" raters. (LMO)

The locally best invariant test statistic for testing sphericity of normal distributions is shown to be a simple function of the Box/Geisser - Greenhouse degrees of freedom correction factor in a repeated measures design. Tables of the critical values of the Box/Geiser - Greenhouse correction factor are given. (Author/BW)

Provides an algorithm for determining the median and quartiles of discrete data sets. Describes the graphical equivalent of the numerical method. (JM)

This study compared two approximations for normalizing noncentral F distributions: one based on the square root of the chi-square distribution (SRA), the other derived from a cube root of the chi-square distribution (CRA). The CRA was superior, and generally provided an excellent approximation for noncentral F. (Author/BW)