Abstract
An analytic approach to standard error and confidence interval estimation of scale reliability with fixed congeneric measures is proposed that is based on a generally applicable estimator stability evaluation procedure, the delta method (e.g., Ogasawara, 1999). The approach complements wide-spread point estimation of composite reliability in behavioral scale construction and development, and can be used to evaluate precision of estimates and plausible ranges for reliability of multiple-component instruments in studied populations. The method is illustrated by means of a numerical example.