Evaluation of Coefficient Alpha for Multiple-Component Measuring Instruments in Complex Sample Designs

作者：Tenko Raykov, Brady Thomas West, Anne Traynor · 发表于：Structural Equation Modeling A Multidisciplinary Journal · 年份：2014 · DOI：10.1080/10705511.2014.936081 · 被引用次数：20 · 研究领域：Optimal Experimental Design Methods、Statistical Methods and Bayesian Inference、Advanced Statistical Methods and Models

A readily applicable procedure for point and interval estimation of coefficient alpha is outlined for complex sample designs, in cases where this coefficient is close to composite reliability. As a by-product, point and interval estimation of the change in alpha due to measuring instrument revision is also possible. This approach can be used as an aid for scale construction and development in empirical investigations involving analyses of complex sample survey data, in particular for secondary data analyses from large-scale studies. The procedure is illustrated with data from an educational survey.