Notes that Career Services Center at University of California-San Diego has conducted career surveys of graduating classes since 1982 and has learned how to conduct survey and use survey data. Discusses how to get started in conducting a graduate survey. Explains how to design survey instrument, draft questions, test survey, distribute survey,…

Reports development of observation system, Preschool Observation Code (POC), for use across phases of preschool intervention design and evaluation. Describes purpose of code, procedures used for code, procedures used for code construction, and two related studies of interrater and criterion-referenced agreement. Discusses practical issues related…

The capability of the DIMTEST statistical test in assessing essential unidimensionality of item responses to real tests was investigated for 22 real tests of at least 25 items and 700 or more examinees. DIMTEST results on real tests were able to discriminate between essentially unidimensional and multidimensional tests. (SLD)

Reports the development of a new geometric analogies test for elementary school children and the examination of its use for future longitudinal studies. Three studies involving 361 elementary school students indicate the quality of the scale and support its use. (SLD)

The ways that portfolio evidence of student competence in the writing processes is created and interpreted were studied in four classrooms during the preliminary trials of the California Learning Assessment System portfolios. Data from interviews with six students and two elementary school teachers are used to explore student portfolios and…

A brief version of the instrument developed by S. Schwartz (1992, 1994) to measure the structure and content of human values was developed. Studies with 199 adults and 420 adults support the reliability of scores produced by the brief inventory's four three-item scales. Uses of the brief form are discussed. (SLD)

A study was conducted in Australia to develop a reliable, valid, and practical measure of atopic dermatitis. The test development process and validity evaluation with two doctors and 51 patients are discussed. Results suggest that operational definitions of the scales need to be defined more clearly. The measure satisfies assumptions for a partial…

Developed a university version of the Charles F. Kettering Climate Scale focusing on psychological dimensions of the educational climate. A second-order analysis of results from 707 students shows areas of generalization across the primary components. (SLD)

Surveys are a commonly-used tool for measuring satisfaction with staff-development workshops. The four main sources of error and bias in most surveys are sampling slips, non-response nonsense, time-slice traps, and questionable questions. The paper discusses several typical survey problems and presents tips for making surveys into effective tools.…

Studied the componential structure of synonym tasks using confirmatory multidimensional two-parameter item-response theory models. Reanalysis of data from 218 and 258 Dutch secondary school students from a previous study (R. Janssen and P. De Boeck, 1997) supports the componential hypothesis. Discusses issues related to one of the subtasks…

Reviews developments in nonparametric item-response theory (NIRT), from its historic origins in item-response theory (IRT) and scale analysis to new theoretical results for practical test construction. Discusses theoretical results from NIRT often relevant to IRT. Contains 134 references. (SLD)

Focuses on the potential contributions of optimal test-design models to practical test-assembly issues that result from limitations in the models or the technology required for their implementation and limitations inherent in the test-assembly process. Outlines research needed to make implementation of these techniques routine in test assembly.…

Describes an integrated approach to test development and administration called computer-adaptive sequential testing (CAST). CAST incorporates adaptive testing methods with automated test assembly. Describes the CAST framework and demonstrates several applications using a medical-licensure example. (SLD)

Proposes two new methods for item-exposure control, the Progressive method and the Restricted Maximum Information method. Compares both methods with six other item-selection methods. Discusses advantages of the two new methods and the usefulness of combining them. (SLD)

This book provides a historical overview of item-response theory (IRT) and contains a compendium of item-response-theory research. Each of its six sections deals with a unique application of a model or a family of models. Requires a strong psychometric background to understand some of the discussions. (SLD)