To test further for efficacy of three-option achievement items, parallel three- and five-option item tests were distributed randomly to college students. Results showed no differences in mean item difficulty, mean discrimination or total test score, but a substantial reduction in time spent on three-option items. (Author/BS)

This paper develops and applies three nonparametric comparisons of the shapes of two item characteristic surfaces: (1) proportional latent odds; (2) uniform relative difficulty; and (3) item sensitivity. A method is presented for comparing the relative shapes of two item characteristic curves in two examinee populations who were administered an…

From 13 objective interview items, five with adequate response variability were studied to determine if they would improve the validity of a verbal ability selection test in predicting work performance of 181 psychiatric aide trainees. In a multiple regression analysis, the verbal test correlated .27 with the weighted composite rating score.…

Using a log-linear modeling approach, the conditional independence of clustered items in the Australian Scholastic Aptitude Test within and between clusters was examined. Data were from 30,465 examinees in Queensland and Western Australia. In general, conditional independence was not found, although the relationships between items were usually…

The effects of statistical and cognitive difficulty ordering of test items, gender, and explicit labeling of item type on college students' test performance were assessed. A total of 137 male and 265 female undergraduates were administered two 40-item multiple choice tests. Results indicate significant effects for gender and use of labels, but…

Discusses the changes needed in General Educational Development (GED) student instruction as a result of the new composition requirement in the GED test. Outlines techniques for teaching composition to GED students. (CH)

Discusses the role computers can play in the administration and scoring of tests and the expanded role of the counseling professional working with computer-assisted testing systems. Computer cost and value, program evaluation, staff training, and counselor and client attitudes toward computer-assisted testing are covered. (Author/ABB)

The applicability of a new multiple-group factor analysis of dichotomous variables is shown and contrasted with the item response theory approach to item bias analysis. Situations are considered where the same set of test items has been administered to more than one group of examinees. (Author/BS).

This study examined the results obtained from certification applicants and practitioners on a national certification examination for clinical laboratory scientists (medical technologists), using a modified Angoff procedure to establish the cut-off score. The major question of the investigation concerned whether the cut-off score was appropriate.…

The wording and structure of questionnaire items can interact with specified sample categories based on evaluation goals and respondent characteristics. The effects of the interactions can restructure samples and introduce bias into the data analysis. These effects, and suggestions for avoiding them, are demonstrated for five types of…

This paper developed and illustrated a technique to analyze categorical data when subjects can appear in any number of categories for multigroup designs. Post hoc procedures to be used in conjunction with the presented statistical test are also developed. The technique is a large sample technique whose small sample properties are as yet unknown.…

Determined how a current sample of college students' (N=301) responses on the Study of Values (SOV) instrument relate to the 1960 norms of the SOV manual. Results showed that economic values were higher and social values were lower than in 1960, suggesting a need for revision of the SOV norms. (LLL)

Though rating scales represent a cost-effective way of obtaining data on child behavior, there are numerous unresolved issues pertaining to their use. This article focuses upon a few considerations regarding the instruments themselves and the informants who provide the ratings. Recommendation for future work on scale development are made.…

Primary school data from the Third International Mathematics and Science Study (TIMSS) were analyzed in this study to examine performance difference between third and fourth grades. The score comparison was conducted across all TIMSS items in each of the 26 participating countries. The empirical findings indicate that not all TIMSS items have…

This paper identifies and assesses key ideas in data analysis (or statistics) that should be at the focus of middle school mathematics instruction. Items that can be used to assess some of the complex objectives of data analysis are located. The search includes a collection of items released by the National Assessment of Educational Progress…