The standard error of measurement usefully provides confidence limits for scores in a given test, but is it possible to quantify the reliability of a test with just a single number that allows comparison of tests of different format? Reliability coefficients do not do this, being dependent on the spread of examinee attainment. Better in this…

This research examines the effect of increased testing time by comparing the four performance indices of randomly equivalent examinee subpopulations on sections of similar content and difficulty administered at different times on three SAT administrations. A variety of analyses were used in this study and found no evidence that the current SAT…

The use of indices and statistics based on nonlinear factor analysis (NLFA) has become increasingly popular as a means of assessing the dimensionality of an item response matrix. Although the indices and statistics currently available to the practitioner have been shown to be useful and accurate in many testing situations, few studies have…

Effects of test length, sample size, and assumed ability distribution were investigated in a multiple replication Monte Carlo study under the 1-parameter (1P) and 2-parameter (2P) logistic graded model with five score levels. Accuracy and variability of item parameter and ability estimates were examined. Monte Carlo methods were used to evaluate…

Rasch between and total weighted and unweighted fit statistics were compared using varying test lengths and sample sizes. Two test lengths (20 and 50 items) and three sample sizes (150, 500, and 1,000 were crossed. Each of the six combinations were replicated 100 times. In addition, power comparisons were made. Results indicated that there were no…

The National Conference of Bar Examiners commissioned American College Testing, Inc., to help them in the development and evaluation of a performance test for use in bar admissions decisions. Because it was recognized that candidate perceptions would provide valuable information, a candidate-perception questionnaire was developed to be…

Two approaches to criterion-referenced test construction are compared. Classical test theory is based on the practice of random sampling from a well-defined domain of test items; latent trait theory suggests that the difficulty of the items should be matched to the achievement level of the student. In addition to these two methods of test…

The viewpoint is expressed that adding to test reliability by either selecting a more homogeneous set of items, restricting the range of item difficulty as closely as possible to the most efficient level, or increasing the number of items will not add to test validity and that there is considerable danger that efforts to increase reliability may…

In most reliability studies, the precision of a reliability estimate varies inversely with the number of examinees (sample size). Thus, to achieve a given level of accuracy, some minimum sample size is required. An approximation for this minimum size may be made if some reasonable assumptions regarding the mean and standard deviation of the test…

This study used a series of simulations to answer questions about the efficacy of adaptive testing raised by empirical studies. The first study showed that for reasonable high entry points, parameters estimated from paper-and-pencil test protocols cross-validated remarkably well to groups actually tested at a computer terminal. This suggested that…

Computerized answer sheets in mail surveys are examined for their effects on rate of return and response bias. Results of an empirical study of job satisfaction suggested that computerized answer sheets may be used in mail surveys without significantly affecting rate of return or producing response bias. (Author/JKS)

Addressing the shortcomings of classical item statistics for selecting criterion-referenced test items, this paper describes an optimal item selection procedure utilizing item response theory (IRT) and offers examples in which random selection and optimal item selection methods are compared. Theoretical advantages of optimal selection based upon…

In computerized adaptive testing (CAT), new or experimental items are frequently administered alongside operational tests to gather the pretest data needed to replenish and replace item pools. The two basic strategies used to combine pretest and operational items are embedding and appending. Variable-length CATs are preferred because of the…

Computer simulations were run to measure the relationship between testlet validity and factors of item pool size and testlet length for both adaptive and linearly constructed testlets. Making a testlet adaptive yields only modest increases in aggregate validity because of the peakedness of the typical proficiency distribution. (Author/SLD)

The purpose of this study was to compare the effects of four item selection rules--(1) Fisher information (F), (2) Fisher information with a posterior distribution (FP), (3) Kullback-Leibler information with a posterior distribution (KP), and (4) completely randomized item selection (RN)--with respect to the precision of trait estimation and the…