The choice of anchor tests is crucial in applications of the nonequivalent groups with anchor test design of equating. Sinharay and Holland (2006, 2007) suggested "miditests," which are anchor tests that are content-representative and have the same mean item difficulty as the total test but have a smaller spread of item difficulties.…

Variation in test performance among examinees from different regions or national jurisdictions is often partially attributed to differences in the degree of content correspondence between local school or training program curricula, and the test of interest. This posited relationship between test-curriculum correspondence, or "alignment,"…

This paper presents six steps in test construction generally recommended by measurement textbook authors. The focus is primarily on paper-and-pencil achievement tests as used by class instructions, although the discussion touches on the construction of other types of assessment. The six steps are: (1) determine the test purpose; (2) determine the…

This study examined initial evidence of changes in fit to a unidimensional model for some language tests at multiple ability levels. Seven data sets were analyzed using the first phase of exploratory factor analysis: principal component eigenvalue extraction. Each data set is analyzed at varying n-sizes: whole group; random subsample; and five…

The Foreign Service Institute (FSI) has been engaged in oral language proficiency testing theory and practice for more than 20 years. The FSI test has been consistent during this time in format, evaluation criteria, performance standards, and level definitions. Current concerns about the degree of standardization of the format and the strength of…

Basic precepts for test development are described and explained as they are presented in measurement textbooks commonly used in the fields of education and psychology. The five building blocks discussed as the foundation of well-constructed tests are: (1) specification of purpose; (2) standard conditions; (3) consistency; (4) validity; and (5)…

Literature related to the multiple true-false (MTF) item format is reviewed. Each answer cluster of a MTF item may have several true items and the correctness of each is judged independently. MTF tests appear efficient and reliable, although they are a bit harder than multiple choice items for examinees. (SLD)

This study examines two kinds of French language tests originating from the Threshold-Level (T-Level) or Niveau-Seuil theory of language learning in the context of several linguistic and testing concepts: discrete-point testing with regard to notions and functions from T-Level theory, communicative context, and assessment of listening…

A one-parameter latent trait model was the basis of the test development procedures in the Basic Skills Assessment Program (BSAP) of the Department of Defense Dependents Schools (DoDDS). Several issues are involved in applying the Rasch model to an assessment program in a large school district. Separate sets of skills continua are arranged by…

This handbook is a guide to the "Test Development Notebook" of the System for Pupil and Program Evaluation and Development (SPPED). It describes the contents and organization of the notebook, suggests various uses of the exercises, provides sample test designs, outlines test production procedures, and offers guidelines for score…

In July 2001, the Ministerial Council on Education, Employment, Training and Youth Affairs (MCEETYA) agreed to the development of assessment instruments and key performance measures for reporting on student skills, knowledge and understandings in primary science. It directed the newly established Performance Measurement and Reporting Taskforce…