A latent variable modeling approach for scale reliability evaluation in heterogeneous populations is discussed. The method can be used for point and interval estimation of reliability of multicomponent measuring instruments in populations representing mixtures of an unknown number of latent classes or subpopulations. The procedure is helpful also…

A method for medical screening is adapted to differential item functioning (DIF). Its essential elements are explicit declarations of the level of DIF that is acceptable and of the loss function that quantifies the consequences of the two kinds of inappropriate classification of an item. Instead of a single level and a single function, sets of…

Measurement invariance (MI) is a property of measurement that is often implicitly assumed, but in many cases, not tested. When the assumption of MI is tested, it generally involves determining if the measurement holds longitudinally or cross-culturally. A growing literature shows that other groupings can, and should, be considered as well.…

In some popular test designs (including computerized adaptive testing and multistage testing), many item pairs are not administered to any test takers, which may result in some complications during dimensionality analyses. In this paper, a modified DETECT index is proposed in order to perform dimensionality analyses for response data from such…

Pennsylvania's Educational Quality Assessment Program provides each participating school with a building level report in which state percentiles are a prominent part. Multiple matrix sampling was being considered as a technique to reduce testing time. However, there was great concern that the error associated with estimating the school mean might…

Nine indices for assessing the accuracy of an individual's test score were evaluated using simulated item responses to a commercial and a classroom test. The indices appear capable of identifying relatively high proportions of examinees with spurious total scores. (Author/PN)

A method for incorporating maximum likelihood (ML) estimation into reliability analyses with item-level missing data is outlined. An ML estimate of the covariance matrix is first obtained using the expectation maximization (EM) algorithm, and coefficient alpha is subsequently computed using standard formulae. A simulation study demonstrated that…

Measures of clinical significance are frequently used to evaluate client change during therapy. Several alternatives to the original method devised by N. S. Jacobson, W. C. Follette, & D. Revenstorf (1984) have been proposed, each purporting to increase accuracy. However, researchers have had little systematic guidance in choosing among…

A 40-item flexilevel test and a 40-item conventional test were compared using data obtained through (1) computer-administration of the two tests to three groups of college students, and (2) monte carlo simulation of test response patterns. Results indicated the flexilevel score distribution better reflected the underlying normal distribution of…

Monte Carlo simulation procedures were used to study the psychometric characteristics of two two-stage adaptive tests and a conventional "peaked" ability test. Results showed that scores yielded by both two-stage tests better reflected the normal distribution of underlying ability. Ability estimates yielded by one of the two stage tests…

A strategy for comparing two sets of results (one based upon early childhood recollections (ECR) and another upon video taped (VT) group behavior) from the Perceptual Characteristics Rating Scale was developed. The null distribution of the mean deviation was estimated by randomly matching an ECR response vector with a VT response vector. To…

The four main approaches to measuring treatment effects in schools; raw gain, residual gain, covariance, and true scores; were compared. A simulation study showed true score analysis produced a large number of Type-I errors. When corrected for this error, this method showed the least power of the four. This outcome was clearly the result of the…

TAILOR is a computer program that uses the implied orders concept as the basis for computerized adaptive testing. The basic characteristics of TAILOR, which does not involve pretesting, are reviewed here and two studies of it are reported. One is a Monte Carlo simulation based on the four-parameter Birnbaum model and the other uses a matrix of…