Compares Illinois' funding formula with a mathematical model for resource compensating formulas. Describes the variables used (including district enrollment, wealth, tax effort, and state guaranteed valuation). Uses graphs to illustrate varying equity effects of the formula for K-12, K-8, and high school districts, both statewide and in selected…

Path analysis was used to provide a comprehensive test of the validity of Tinto's causal model of voluntary withdrawal from a postsecondary institution. This study also tests Tinto's hypothesis of compensatory interactions between social and academic integration and between institutional and goal commitment. (Author/PN)

A model is presented using examinee judgements in detecting ambiguous/misinterpreted items on teacher-made criterion-referenced tests. A computational example and guidelines for constructing domain categories and interpreting the indices are presented. (Author/PN)

Applications of an LR-1 parsing algorithm to intelligent programs for computer assisted instruction in symbolic logic and foreign languages are discussed. The system has been adequately used for diverse instructional applications, including analysis of student input, generation of pattern drills, and modeling the student's understanding of the…

Analysis of a survey of freshman women at a land-grant university included 12 possible determinants of student satisfaction, intent to leave the college, and dropout. The labor model seems applicable to colleges and universities, but is not sufficient to explain the dropout process. (MSE)

Develops a model of teacher salaries and teacher supply and demand, including production functions, occupational choice, budget constraints, and district income and tax rates, as an aid in analyzing educational finance reforms. Tests the model on Pennsylvania school district data, using three different assumptions about labor market competition…

Believing that examinee-by-item interaction should be conceptualized as true score variability rather than as a result of errors of measurement, Lu proposed a modification of Hoyt's analysis of variance reliability procedure. Via a computer simulation study, it is shown that Lu's approach does not separate interaction from error. (Author/RL)

The Rasch simple logistic model is used to examine the relative item parameter values of a personality inventory with respect to populations cross-classified by sex and country. While items conform to the model within each of the populations, half the items show significant discrepancies among the populations. (Author/RL)

Analysis of multivariate aptitude-treatment-interaction data is discussed. Analysis procedures are illustrated using data from a science education study to describe the interaction between student reading ability and the time allowed in an individualized instructional approach for multiple achievement and attitudinal outcomes. (Author/RL)

While some forms of test bias (for example, bias in selection and prediction) appear amenable to definitional consensus, a definition of cultural bias will remain problematic so long as it is confused with the nature/nurture issue. (Author/BW)

Data on 2,380 searches of online information retrieval systems are analyzed using a mathematical model to determine the relationship between two measures of effectiveness--documents read and relevant references. The nature and relative merits of these two variables are discussed, as well as the findings, and seven references are listed. (RBF)

Describes a three-hour, one-semester graduate course to provide numerical methods and modeling techniques to handle problems in future courses or engineering practice. Includes rationale for topics such as interpolation, integration, and equation roots, among others. Indicates that all problems require computer use. (SK)

Productivity, novelty, figures of speech, flexibility, and elaboration were hypothesized to represent teachers' judgments of creativity of essay compositions. Essays were scored on the five dimensions and teachers judged essay creativity independently. Teachers' judgments were reliable, and four of the five dimensions correlated with rated…

Computer generated data are used to show that Slinde and Linn's criticism of the usefulness of the Rasch model for equating (EJ 189 585) may have been the result of an artifact produced by the manner in which the samples were chosen in their study. (CTM)

Explains methods used by the Mississippi state department of education to reimburse local school districts for vocational expenditures. Different sources of data are reported and methods for arriving at specific reimbursement rates for both secondary and postsecondary programs are depicted. (LRA)