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…

This chapter introduces theory that undergirds the role of testing adaptations in assessment, provides examples of item modifications and testing accommodations, reviews research relevant to each, and introduces a new paradigm that incorporates opportunity to learn (OTL), academic enablers, testing adaptations, and inferences that can be made from…

Unreliable profiles impose the difficulty that ordinal and interval relations among the individual's scores become uncertain or unstable. A profile reliability coefficient is derived to estimate the relative expected extent of this ordinal and interval "inversion" for any profile of K measures. (Author/DWH)

Both the attenuation paradox of traditional test theory and the assumption of local independence in person-item response theory have caused problems in interpretation. This paper demonstrates that the two are related concepts, and, through this demonstration, both are clarified. It is demonstrated that the breakdown of local independence leads to…

It is suggested that error of measurement cannot be routinely incorporated into the "error term" in statistical tests, and that the reliability of test scores does not have the simple relationship to statistical inference that one might expect. (Author/GK)

Reliability coefficients of linear combinations of observed scores have anomalous properties which have led to difficulties in the investigation of difference scores and gain scores in test theory. Discrepancies between classical results and correct results obtained from more general formulas, which allow for correlated errors, are examined…

Issues concerning equating test scores are discussed in an introduction, four papers, and two commentaries. Equating methods research, sampling errors, linear equating, population differences, sources of equating errors, and a circular equating paradigm are considered. (SLD)

Test scores that are not perfectly reliable cannot be strictly equated unless they are strictly parallel. This fact implies that tau equivalence can be lost if an equipercentile equating is applied to observed scores that are not strictly parallel. Thirty-six simulated data sets are produced to simulate equating tests with different difficulties…

An important determinant of equating process efficiency is the correlation between the anchor test and components of each form. Use of some monotonic function of this correlation as a measure of equating efficiency is suggested. A model relating anchor test length and test reliability to this measure of efficiency is presented. (Author/DWH)

A behavioral domain is well-defined when it is clear to both test developers and test users which categories of performance should or should not be considered for potential test items. Only those tests that are keyed to well-defined domains meet the definition of criterion-referenced tests. The greatest proliferation of criterion-referenced tests…

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…

These studies in test adequacy focus on two problems: procedures for estimating reliability, and techniques for identifying ineffective distractors. Fourteen papers are presented on recent advances in measuring achievement (a response to Molenaar); "an extension of the Dirichlet-multinomial model that allows true score and guessing to be…

A critical review of the Expressive One-Word Picture Vocabulary Test (Gardner) is offered. The reviewer feels that the instrument cannot be recommended in its present form. Further research concerning the manual, and theoretical issues, (particularly test-retest stability) is strongly recommended. (Author/PN)

Issues surrounding accurate assessment of depression in children have received much attention. However, the stability of scores from depression measures has generally been estimated using only classical test score theory, rather than the more powerful generalizability theory. The dependability of scores from the Children's Depression Inventory…

Presents major stages in design and development of criterion referenced tests (CRT) with emphasis on differences between CRT construction and norm-referenced test construction. Discussion covers test interpretation; test theory; preparation for test construction (hierarchical analysis, item type selection, and choosing number of items); test…