The problem of factor score indeterminacy implies that the factor and the error scores cannot be completely disentangled in the factor model. It is therefore proposed to compute Harman's factor score predictor that contains an additive combination of factor and error variance. This additive combination is discussed in the framework of classical…

Increasingly, researchers interested in identifying potentially biased test items are encouraged to use a confirmatory, rather than exploratory, approach. One such method for confirmatory testing is rooted in differential bundle functioning (DBF), where hypotheses regarding potential differential item functioning (DIF) for sets of items (bundles)…

Three multiple indicators-multiple causes (MIMIC) methods, namely, the standard MIMIC method (M-ST), the MIMIC method with scale purification (M-SP), and the MIMIC method with a pure anchor (M-PA), were developed to assess differential item functioning (DIF) in polytomous items. In a series of simulations, it appeared that all three methods…

Conservative bias in rejection of a null hypothesis from using the continuity correction in the Mantel-Haenszel (MH) procedure was examined through simulation in a differential item functioning (DIF) investigation context in which statistical testing uses a prespecified level [alpha] for the decision on an item with respect to DIF. The standard MH…

A marginal maximum a posteriori (MMAP) procedure was implemented to estimate item parameters in the generalized graded unfolding model (GGUM). Estimates from the MMAP method were compared with those derived from marginal maximum likelihood (MML) and Markov chain Monte Carlo (MCMC) procedures in a recovery simulation that varied sample size,…

To realize the benefits of item response theory (IRT), one must have model-data fit. One facet of a model-data fit investigation involves assessing the tenability of the conditional item independence (CII) assumption. In this Monte Carlo study, the comparative performance of 10 indices for identifying conditional item dependence is assessed. The…

This article describes two methods for obtaining the standard errors of two commonly used population invariance measures of equating functions: the root mean square difference of the subpopulation equating functions from the overall equating function and the root expected mean square difference. The delta method relies on an analytical…

Person-fit methods are used to uncover atypical test performance as reflected in the pattern of scores on individual items in a test. Unlike parametric person-fit statistics, nonparametric person-fit statistics do not require fitting a parametric test theory model. This study investigates the effectiveness of generalizations of nonparametric…

Semantic incompatibility, an error in constructing measuring instruments for rating oneself, others, or objects, refers to the extent to which item wordings are incongruent with, and hence inappropriate for, scale labels and vice versa. This study examines the effects of semantic incompatibility on rating responses. Using a 2 x 2 factorial design…

This note shows that, under conditions specified by Levin and Subkoviak (TM 503 420), it is not necessary to specify the reliabilities of observed scores when comparing completely randomized designs with randomized block designs. Certain errors in their illustrative example are also discussed. (Author/CTM)

Comments (TM 503 706) on an earlier article (TM 503 420) concerning the comparison of the completely randomized design and the randomized block design are acknowledged and appreciated. In addition, potentially misleading notions arising from these comments are addressed and clarified. (See also TM 503 708). (Author/CTM)

This note continues the discussion of earlier articles (TM 503 420, TM 503 706, and TM 503 707), comparing the completely randomized design with the randomized block design. (CTM)

A statistical test for detecting answer copying on multiple-choice tests based on Cohen's kappa is proposed. The test is free of any assumptions on the response processes of the examinees suspected of copying and having served as the source, except for the usual assumption that these processes are probabilistic. Because the asymptotic null and…

Type I error rates were examined for several fit indices available in GGUM2000: extensions of Infit, Outfit, Andrich's X(2), and the log-likelihood ratio X(2). Infit and Outfit had Type I error rates much lower than nominal alpha. Andrich's X(2) had Type I error rates much higher than nominal alpha, particularly for shorter tests or larger sample…

For six tests, coefficient delta as an index for internal optimality is computed. Internal optimality is defined as the magnitude of risk of the decision procedure with respect to the true score. Results are compared with an alternative index (coefficient kappa) for assessing the consistency of decisions. (Author/JKS)