This discussion paper argues that both the use of Cronbach's alpha as a reliability estimate and as a measure of internal consistency suffer from major problems. First, alpha always has a value, which cannot be equal to the test score's reliability given the inter-item covariance matrix and the usual assumptions about measurement error. Second, in…

We make theoretical comparisons among five coefficients--Cronbach's [alpha], Revelle's [beta], McDonald's [omega][sub h], and two alternative conceptualizations of reliability. Though many end users and psychometricians alike may not distinguish among these five coefficients, we demonstrate formally their nonequivalence. Specifically, whereas…

Under the assumption of normalcy, a formula is derived for the reliability of the maximum score. It is shown that the maximum score is more reliable than each of the single observations but less reliable than their composite score. (Author/LMO)

This paper presents a row-column (RC) association model in which the estimated row and column scores are forced to be in agreement with a priori specified ordering. Two efficient algorithms for finding the order-restricted maximum likelihood (ML) estimates are proposed and their reliability under different degrees of association is investigated by…

Scoring of response vectors to give maximum test-retest correlation is investigated. A general method is given for finding the best scores, deriving them for the normal factor model, and showing that for a standard model for binary response it is easy to approximate the best scores. (SLD)

A technique is presented to transform incomplete categorical data into complete data by imputing appropriate scores into missing cells. A solution of the optimization problem is suggested, and relevant psychometric theory is discussed. The average correlation should be at least 0.50 before the method becomes practical. (SLD)

Three methods for estimating reliability are studied within the context of nonparametric item response theory. Two were proposed originally by Mokken and a third is developed in this paper. Using a Monte Carlo strategy, these three estimation methods are compared with four "classical" lower bounds to reliability. (Author/JAZ)

A model and computation procedure based on classical test score theory are presented for determination of a correlation coefficient corrected for attenuation due to unreliability. Delta and Monte Carlo method applications are discussed. A power analysis revealed no serious loss in efficiency resulting from correction for attentuation. (TJH)

Bias, standard error, and reliability of five ability estimators were evaluated using Monte Carlo estimates of the unknown conditional means and variances of the estimators. Results indicate that estimates based on Bayesian modal, expected a posteriori, and weighted likelihood estimators were reasonably unbiased with relatively small standard…