This book discusses adapting pencil-and-paper tests to computerized testing. Mention is made of models for graded responses to items and of possibilities beyond pencil-and-paper-tests, but the book is essentially about dichotomously scored test items. Contrasts between item response theory and classical test theory are described. (SLD)

The clarification provided by Williams and Zimmerman on the reliability of gain scores is translated into recognizable patterns of change that tend to produce reliable or unreliable gain scores. The relevance of the traditional idea of reliability to the measurement of change is also discussed. (SLD)

Reviews the most recent version of the BILOG computer program, which estimates item and trait level parameters for the one-, two-, and three-parameter logistic unidimensional Item Response Models for dichotomously scored data. Finds this version useful. (SLD)

The reliability of a gain is determined by the reliabilities of the components, the correlation between them, and their standard deviations. Reliability is not inherently low, but the components of gains in many investigations make low reliability likely and require caution in the use of gain scores. (SLD)

The critiques by L. Collins and L. Humphreys in this issue illustrate problems with the use of gain scores. Collins' examples show that familiar formulas for the reliability of differences do not reflect the precision of measures of change. Additional examples demonstrate flaws in the conventional approach to reliability. (SLD)