Issues concerning the selection of judges for standard setting are discussed. Determining the consistency of judges' recommendations, or their congruity with other expert recommendations, would help in selection. Enough judges must be chosen to allow estimation of recommendations by an entire population of judges. (SLD)

This paper discusses standard error of measurement (SEM), the amount of variation or spread in the measurement errors for a test, and gives information needed to interpret test scores using SEMs. SEMs at various score levels should be used in calculating score bands rather than a single SEM value. (SLD)

Statistical methods for program evaluation with nonexperimental data are reviewed with emphasis on circumstances in which nonexperimental data are valid. Three solutions are proposed for problems of selection bias, and implications for evaluation design and data collection and analysis are discussed. (SLD)

Effects of the following variables on performance of computerized adaptive testing (CAT) procedures for the partial credit model (PCM) were studied: (1) stopping rule for terminating CAT; (2) item pool size; and (3) distribution of item difficulties. Implications of findings for CAT systems based on the PCM are discussed. (SLD)

A version of the randomized response survey unrelated question technique is presented in which the answer to the unrelated question is known to be yes. Raw data become a direct linear transformation of response to the sensitive question and can be used in analysis at the individual level. (SLD)

Presents three teaching strategies requiring active student participation in which students (1) create and solve their own word problems; (2) generate trigonometric expressions to be solved by their classmates; and (3) act as points to model a basic locus of points. (MDH)

Changes in information retention resulting from changes in reliability and number of intervals in scale construction were studied to provide quantitative information to help in decisions about choosing intervals. Information retention reached a maximum when the number of intervals was about 8 or more and reliability was near 1.0. (SLD)

Mokken models of monotone homogeneity and double monotonicity and the Rasch model are compared using data from 990 young adult examinees taking a Dutch verbal intelligence test--the Verbal Analogies Test. The model of monotone homogeneity was found suitable for basic testing; more sophisticated applications appear to require parametric models.…

Emphasizes a real-world-problem situation using sine law and cosine law. Angles of elevation from two tracking stations located in the plane of the equator determine height of a satellite. Calculators or computers can be used. (LDR)

The application of time series analysis is described, focusing on the use of regression analysis for analyzing time series in a way that may make it more readily available to an evaluation practice audience. Practical guidelines are suggested for decision makers in government, health, and social welfare agencies. (SLD)

An eclectic approach is presented for the evaluation of services to the homeless. The method combines social network analysis and multiattribute technology to allow for development of a criterion for evaluation of services for a geographic area. Service delivery configuration, evaluation criteria, and a planning and monitoring strategy are…

Evidence is presented on the generalizability and convergent validity of performance assessments using data from six studies of student achievement that sampled a wide range of measurement facets and methods. Results at individual and school levels indicate that task-sampling variability is the major source of measurement error. (SLD)

Presents a methodology of mathematical and technological principles as integrated components of the Design and Technology syllabus of the National Curriculum in the United Kingdom. The methodology is based on the syllabus area of product analysis and employs a structured problem-solving approach. (ASK)

Estimates earnings reported by 219 recent college graduates and earnings expected by 248 college seniors, considering seven variables. Although students' expectations generally accord with recent graduates' marketplace experiences, students underestimate the earnings outcome of working more hours and overestimate age effects. The model holds truer…

Drawing on empirical studies from five countries (Netherlands, Spain, Portugal, United Kingdom, and United States), over 2 decades, outlines irregularities in the incidence of over- and under-education and consequences for individual earnings. The overall incidence of overeducation in the labor market is about 26 percent. (Contains 33 references.)…