A paradoxical phenomenon of decreases in reliability as the number of elements averaged over increases is shown to be possible in multifacet reliability procedures (intraclass correlations or generalizability coefficients). Conditions governing this phenomenon are presented along with implications and cautions. (Author)

This handbook will assist principals and school testing coordinators in implementing the spring 2007 administration of the Developmental Reading Assessment (DRA). Information regarding administration timeline, reporting, process, online tools and contact personnel is discussed. Contents include: (1) Scheduling; (2) Identify Primary Test…

Finds that the time required to attempt all the test items of each question paper in a four-paper sample was inversely proportional to the percentage of students who attempted all the test items of that paper. Extrapolates results to give guidelines for determining the feasibility of newly-developed exam papers. (WRM)

The testlet, a bundle of test items, alleviates some problems associated with computerized adaptive testing: context effects, lack of robustness, and item difficulty ordering. While testlets may be linear or hierarchical, the most useful ones are four-level hierarchical units, containing 15 items and partitioning examinees into 16 classes. (GDC)

A problem of considerable importance in certain educational settings is determining how many items to include on a mastery test. Applying ranking and selection procedures, a solution is given which includes as a special case all existing single-stage, non-Bayesian solutions based on a strong true-score model. (Author/JKS)

As adaptive testing moves toward operational implementation in large scale testing programs, where it is important that adaptive tests be as parallel as possible to existing linear tests, a number of practical issues arise. This paper concerns three such issues. First, optimum item pool size is difficult to determine in advance of pool…

Because latent trait models require that large numbers of items be calibrated or that testing of the same large group be repeated, item parameter estimates are often obtained by administering separate tests to different groups and "linking" the results to construct an adequate item pool. Four issues were studied, based upon the analysis…

In mastery testing a linear relationship between an optimal passing score and test length is presented with a new optimization criterion. The usual indifference zone approach, a binomial error model, decision errors, and corrections for guessing are discussed. Related results in sequential testing and the latent class approach are included. (CM)

A series of behavioral expectation scale applications were analyzed in an attempt to point out an appropriate number of dimensions to be included in such studies. Results reflected the problems of dimension interdependence when the number of dimensions exceeds nine. (Author/JKS)

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 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…

Tailored testing provides the same information as group-administered standardized tests, but can do so using fewer items because the items administered are selected for the ability of the individual student. Thus, tailored testing offers several advantages over traditional methods. Because individual tailored tests are not timed, anxiety is…

The problem of determining optimal test lengths with fixed total testing time has proved to be a difficult one for criterion-referenced test developers. An algorithm is needed which can be used by test developers to allocate available testing time to maximize the validity of their total criterion-referenced tests or testing programs. To be…

To examine the validity of short forms of the Wechsler Intelligence Scale for Children-Revised (WISC-R), the WISC-R was first administered to 106 hospitalized psychiatric patients, aged 8-16. No subjects had a primary diagnosis of mental retardation or learning disability, and one-third were receiving psychotropic medication. WISC-R IQ scores…

Mastery tests are analyzed in terms of the number of skills to be mastered and the number of items per skill, in order that correct decisions of mastery or nonmastery will be made to a desired degree of probability. It is assumed that a random sample of skills will be selected for measurement, that each skill will be measured by the same number of…