Presents a variation of a "greedy" algorithm that can be used in test-assembly problems. The algorithm, the normalized weighted absolute-deviation heuristic, selects items to have a locally optimal fit to a moving set of average criterion values. Demonstrates application of the model. (SLD)

The sampling interpretation of confidence intervals and hypothesis tests is discussed in the context of conditional maximum likelihood estimation. Three different interpretations are discussed, and it is shown that confidence intervals constructed from the asymptotic distribution under the third sampling scheme discussed are valid for the first…

The Decisional Process Inventory is a Gestalt theory-based measure of career decision-making and level of career indecision. Results from a sample of 183 undergraduates supported its content, construct, and concurrent validity. (SK)

The Career Decision Profile can be used by counselors to explore a client's career indecision, screen for readiness, determine services needed, and evaluate outcomes. A survey of five counselors identified reasons why The Profile is or is not being used. (SK)

Study uses confirmatory factor analysis to assess four models of the Hong Psychological Reactance Scale (HPRS) and attempts to provide psychometric information about the subscales. Results found inadequate fit for Hong's four orthogonal models but sufficient fit for two nonorthogonal models. (Contains 29 references and 3 tables.) (GCP)

Psychometric testing in the workplace influences who gets promoted, transferred, or mentored. The objective of such tests as the Myers Briggs Type Indicator is to forecast a worker's ability to fill a certain role in an organization and predict future behavior. (Author/JOW)

Item-discrimination indices are numbers calculated from test data that are used in assessing the effectiveness of individual test questions. This article asserts that the indices are so unreliable as to suggest that countless good questions may have been discarded over the years. It considers how the indices, and hence overall test reliability,…

To determine the factors that contribute to or compromise the effectiveness of multiscored items, this study combined analysis of statewide score data from the 1996 Maryland School Performance Assessment Program tests with systematic analyses of 60 activities providing measures of writing, language usage, or both, and one or more content areas.…

Explores three issues to consider regarding statewide standardized tests in higher education: (1) existing statewide testing programs differ markedly from one another in nature and objectives, and it's important to know specifically how and why; (2) a range of substantial implementation issues will be present; and (3) there are promising…

Examined how knowledge associated with verbs can be impaired by brain damage. A standardized battery of tests was administered to a group of brain damaged subjects. The goal was to investigate how patterns of associations and dissociations that emerged across tests could shed light on the functional architecture that underlies the meaning of verbs…

Examined the historical growth in the popularity of statistical significance testing using a random sample of data from 12 American Psychological Association journals. Results replicate and extend findings from a study that used only one such journal. Discusses the role of statistical significance testing and the use of replication and…

The Hubbard and Ryan article is a little ingenuous in its implications for action. Both meta-analyses and replication have problems of their own; each requires careful attention. Good measurement emphasizes proper sampling techniques and using whatever means possible to analyze data. (SLD)

Agrees with R. Hubbard and P. Ryan that statistical significance testing has had a negative impact in that some users have closed their minds to alternative approaches to conducting research. In marketing, the alternatives are not completely satisfactory, however, and researchers are likely to continue to rely on statistical significance testing.…

Provides a brief historical review of construct validity and discusses the current state of validity theory, emphasizing the role of arguments in validation. Examines the application of an argument-based approach with regard to the distinction between performance-based and theory-based interpretations and the role of consequences in validation.…

Presents simple and direct demonstrations showing why basic measurement principles require that biases in data created by measurement error be removed. Refutes common objections to the correction for these biases. Also describes substantive psychological processes responsible for some types of measurement error. (SLD)