This study investigated the group invariance of equating results using a science achievement test. Examinees were divided into different subgroups based on the average composite score for test centers, whether they had taken a physics course, and self-reported science grade point average. The reason for dividing examinees into subgroups using such…

Rasch model vertical equating procedures were applied to three mathematics computation tests for grades six, seven, and eight. Each level of the test was composed of 45 items in three sets of 15 items, arranged in such a way that tests for adjacent grades had two sets (30 items) in common, and the sixth and eighth grades had 15 items in common. In…

Uses of the variety of scores generated by standardized achievement tests are discussed. Desirable characteristics of scales, raw score scales, percent of correct items, percentile ranks, grade equivalents, normal curve equivalents, and scale scores are considered. The various meanings and purposes of each type of score are discussed. It is…

The Rasch model was used to compare the grade equivalent scores which students of equal ability would have obtained, had they taken different levels of the Iowa Tests of Basic Skills (ITBS). Raw scores on items common to levels 9-14 of the ITBS (vocabulary subtest) were obtained from 6,000 students in Dallas, Texas. Rasch scales were used to…

The objective of this study was to show that standardized reading scores could be adequately estimated from scores on a criterion-referenced test in reading. This would reduce classroom test time, while, at the same time, provide the kinds of information teachers need to guide instruction, and the kinds of information administrators require for…

Both on-level and out-of-level tests were administered to third and fifth grade children in order to compare the scaled scores of different level tests of the same testing program and to discover whether the relationship between levels might be distorted by ceiling or floor effects. Only reading tests were used in this study. The Stanford…

Goodness of fit of raw test score data were compared, using two latent trait models: the Rasch model and the Birnbaum three-parameter logistic model. Data were taken from various achievement tests and the Scholastic Aptitude Test (Verbal). A minimum sample size of 1,000 was required, and the minimum test length was 40 items. Results indicated that…

Concern was expressed for the possible effects of testing Elementary Secondary Education Act (ESEA) Title I students with norm-referenced tests that may be so difficult that many students will have scores in the chance range. The likelihood of such students obtaining equal scaled scores if they were tested with easier out-of-level tests was…

Fourth, seventh, and ninth grade students in Elementary Secondary Education Act (ESEA) Title I programs were tested with the reading comprehension subtests of the Comprehensive Tests of Basic Skills, at each of two levels: on-level for each respective grade, and an easier out-of-level form. Approximately half of these students were found to be…