Four discrimination indices were compared, using score distributions which were normal, bimodal, and negatively skewed. The score distributions were systematically varied to represent the common circumstances of a military training situation using criterion-referenced mastery tests. Three 20-item tests were administered to 110 simulated subjects.…

This report presents a compilation of national statistics on the not-for-profit and commercial arts fields and is intended to serve as a reference book for arts statistics. The focus is on nationally representative data collected through research efforts and donations of statistical information by arts related organizations. The statistics are…

In response to the increasing importance of student performance in required classes, research was conducted to compare two prediction procedures, linear modeling using multiple regression and nonlinear modeling using AID3. Performance in the first college math course (College Mathematics, Calculus, or Business Calculus Matrices) was the dependent…

The Pennsylvania Educational Quality Assessment data have consistently shown differences between rural, suburban, and urban schools in terms of performance on goal areas and on important background variables. The most consistent pattern has been demonstrated by achievement on cognitive measures. The analyses reported upon were conducted on the…

A procedure for developing a costing model is described. Limitations of a cost analysis are also reviewed, with attention to the problems of handling joint products, obtaining accurate faculty effort data, measuring educational outputs, and calculating marginal costs. A researcher charged with developing a costing model is faced with the task of…

Several models for optimizing incomplete sample designs with respect to information on the item parameters are presented. The following cases are considered: (1) known ability parameters; (2) unknown ability parameters; (3) item sets with multiple ability scales; and (4) response models with multiple item parameters. The models are able to cope…

This report presents statistics on the 107 university libraries and 12 independent research libraries that were members of the ARL (Association of Research Libraries) during the 1987-88 fiscal year. Data are reported in alphabetical and rank order on collections (volumes in library, gross and net volumes added, monographs purchased, current…

To compile its projections of future employment levels, the Bureau of Labor Statistics (BLS) combines the following five interlinked models in a six-step process: a labor force model, an econometric model of the U.S. economy, an industry activity model, an industry labor demand model, and an occupational labor demand model. The BLS was asked to…

The value-added model is presented as a method of assessing the impact of treatments in pretest-posttest quasi-experimental designs. The model yields a projection of treatment group performance at posttest time with no special treatment. The difference between the expected result and the actual outcome is "the value added," a measure of…

The communication of research findings among collegiate institutional researchers is considered in relation to the contribution of qualitative language in general, and catastrophe theory in particular. The qualitative language of catastrophe theory may help reduce the arbitrariness of description, through identification of qualitative features…

This report describes the initial development of the Vocational Interest Survey (VIS), which is comprised of six experimental scales for the measurement of Holland's vocational typology. The initial item pool was generated by the free-association written responses of high school students. Occupational titles were selected for inclusion in a pilot…

This study investigated six statistical merit school selection methods using student scores on a nationally normed, standardized achievement test to identify merit schools. More specifically, its purpose was to select a method for the Palm Beach County School system which meets the Florida merit school program criterion of fairness in terms of…

Two approaches for conceptualizing and estimating a contextual model for analyzing student achievement are the separate equation approach and the single equation approach. The separate equation method determines the relationship between the individual-level independent variable and the individual-level dependent variable within each group. It then…

Research on factors that influence college choice, including sociologic and economic explanations, is reviewed. It is suggested that the following four factors strongly affect college choice: family background, student achievement or ability, some college attributes, and labor-market conditions. School context and college effects moderately affect…

To investigate locus of control and its relationships to ethnicity, socioeconomic status (SES), and academic achievement, a large sample of Black, Mexican-American, Native American, and White students in the fourth, fifth, and seventh grades were administered the Academic Achievement Accountability Questionnaire (a locus-of-control questionnaire)…