LONGITUDINAL MEASUREMENT MODELS IN EVALUATION RESEARCH - EXAMINING STABILITY AND CHANGE

This article provides an introduction to the use of Confirmatory Facto r Analysis to test measurement invariance and stability in longitudina l research. The approach is illustrated through examples representing: (a) one construct, two measurement waves; (b) one construct, three wa ves; (c) two constructs, two waves; and (d) comparison of treatment an d control groups in pre-post designs. Basic issues in establishing mea surement invariance over time, across treatment groups, and within mea surement waves are discussed. Estimates of the stability coefficients that are corrected for measurement error and method variance associate d with each specific measured variable are provided. Establishing meas urement invariance is a critical requirement for making inferences abo ut treatment effects and changes in constructs overtime. Copyright (C) 1996 Elsevier Science Ltd