A procedure is described for estimating the reliability and conditional standard errors of measurement of scale scores incorporating the discrete transformation of raw scores to scale scores. The method is illustrated using a strong true score model, and practical applications are described. (SLD)

Effects of passage and item-scrambling on equipercentile and item-response theory equating were investigated using 2 scrambled versions of the American College Testing Program Assessment for approximately 25,000 examinees. Results indicate that using a base-form conversion table with a scrambled form affects the individual examinee level. (SLD)

This user handbook includes four main sections: (1) components of the American College Testing (ACT) Program Assessment; (2) ACT Assessment Reports and Data Services; (3) using ACT student data; and (4) ACT assessment participation. The components described are the four tests of educational development, the High School Course/Grade Information…

This report provides information about the performance of 1991 graduating seniors nationwide who took the American College Testing (ACT) Program Assessment as juniors or seniors. All the average scores in this report are on the scale for the Enhanced ACT Assessment, which was introduced in October 1989. Averages for 1987-89 are based on scores…

This manual contains preliminary information, largely of a technical nature, about the enhanced American College Testing (ACT) Program introduced in October 1989. It focuses primarily on the tests of educational development, the component of the program that has been substantially revised. Although one-third of the ACT Interest Inventory Items has…

Statistics in this report reflect characteristics of 1991 graduates from a given school (individual data, however, are not provided in this sample) who took the American College Testing (ACT) Program assessment. A 5-year trend history of college-bound students is provided. The following tables are presented: (1) average ACT scores by academic…