This paper reports a method for assessing the adequacy of existing item banks for computer adaptive testing. The method takes into account content specifications, test length, and stopping rules, and can be used to determine if an existing item bank is adequate to administer a computer adaptive test efficiently across differing levels of examinee…

It is unrealistic to suppose that standard item response theory (IRT) models will be appropriate for all new and currently considered computer-based tests. In addition to developing new models, researchers will need to give some attention to the possibility of constructing and analyzing new tests without the aid of strong models. Computerized…

Several person-fit statistics have been proposed to detect item score patterns that do not fit an item response theory model. To classify response patterns as not fitting a model, a distribution of a person-fit statistic is needed. The null distributions of several fit statistics have been investigated using conventionally administered tests, but…

Some cognitive psychologists, who have tried to approach psychometric theories, say that the psychometric approach does not provide them with theories and methods with which they can deal with differential strategies. In this paper, a general latent trait model for differential strategies in cognitive processes is proposed which includes three…

One form of adaptive testing involves a two-stage procedure. The first stage is the administration of a routing test. From this first test, an estimate of an examinee's ability is obtained. On the basis of this ability estimate, a second test focused on a given ability level is administered. The purpose of this study was to compare the efficiency…

In defense of retaining the "latent trait theory" term, instead of replacing it with "item response theory" as some recent research would have it, the following objectives are outlined: (1) investigation of theory and method for estimating the operating characteristics of discrete item responses using a minimum number of…

In the methods and approaches developed for estimating the operating characteristics of the discrete item responses, the maximum likelihood estimate of the examinee based upon the "Old Test" has an important role. When Old Test does not provide a sufficient amount of test information for the upper and lower part of the ability interval,…

A series of four vocabulary norming tests was used to develop a large, homogeneous pool of vocabulary test items for use in computer-administered adaptive testing research. Five hundred seventy-five unique vocabulary knowledge items were divided among the four norming tests, and administered to separate groups of college undergraduates. Norming…

A two-stage adaptive test and a conventional peaked test were constructed and administered on a time-shared computer system to students in undergraduate psychology courses. (The two-stage adaptive test consisted of a routing test followed by one of a series of measurement tests.) Comparison of the score distributions showed that the two-stage test…

Several important implications in latent trait theory, with implications for individualized or tailored testing, are pointed out. A way of using the information function in tailored testing in connection with the standard error estimation of the ability level using maximum likelihood estimation is suggested. (Author/JKS)

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)

An experiment was conducted that contrasted a variant of computerized adaptive testing, self-adapted testing, with two traditional tests. Participants completed a self-report of text anxiety and were randomly assigned to take one of the three tests of verbal ability. Subjects generally chose more difficult items as the test progressed. (Author/LMO)

This study examines the effect of item response time across 30 items on ability estimates in a high stakes computer adaptive graduate admissions examination. Examinees were categorized according to 4 item response time patterns, and the categories are compared in terms of ability estimates. Significant differences between response time patterns…

Information provided for computerized adaptive test (CAT) simulees was compared under two conditions on two moderately correlated trait composites, mathematics and reading comprehension. The first condition used information provided by in-scale items alone, while the second condition used information provided by in- and out-of-scale items together…

Recent developments of person-fit analysis in computerized adaptive testing (CAT) are discussed. Methods from statistical process control are presented that have been proposed to classify an item score pattern as fitting or misfitting the underlying item response theory (IRT) model in a CAT. Most person-fit research in CAT is restricted to…