The formula developed by R. Levine (1955) for equating unequally reliable tests is described. The formula can be interpreted as a method of moments estimate of an equating function that results in first order equity of the equated test score under a classical congeneric model. (TJH)

Coefficient alpha was examined through computer simulation as an estimate of test reliability under violation of two assumptions. Coefficient alpha underestimated reliability under violation of the assumption of essential tau-equivalence of subtest scores and overestimated it under violation of the assumption of uncorrelated subtest error scores.…

The use of confirmatory factor analysis by the LISREL program is demonstrated as an assumption-testing method when computing reliability coefficients under different model assumptions. Results indicate that reliability estimates are robust against departure from the assumption of parallelism of test items. (SLD)

A brief overview is provided of the Conger-Lipshitz approach to estimating the reliability of a profile or test battery. A computational example from a recent study shows how canonical reliability can be obtained through existing statistical software. (SLD)

This report describes a statistically designed experiment that was carried out in an operational setting to determine the contributions of different sources of variation to the unreliability of scoring. The experiment made novel use of partially balanced incomplete block designs that facilitated the unbiased estimation of certain main effects…

Generalizability theory (G-theory) and many-facet Rasch measurement (Rasch) manage the variability inherent when raters rate examinees on test items. The purpose of G-theory is to estimate test reliability in a raw score metric. Unadjusted examinee raw scores are reported as measures. A variance component is estimated for the examinee…

This computer program, written in BASIC, performs three different calculations of test reliability: (1) the Kuder-Richardson method; (2); the "common split-half" method; and (3) the Rulon-Guttman split-half method. The program reads sequential access data files for microcomputers that have been set up by statistical packages such as…

Much previously published material for estimating the reliability of classification has been based on the assumption that a test consists of a known number of equally weighted items. The test score is the number of those items answered correctly. These methods cannot be used with classifications based on weighted composite scores, especially if…

Statistical significance and "abnormality" have been used as criteria for the evaluation of intra-individual subtest score differences. Shortcomings of these criteria are identified, and improved estimates of the true score differences are suggested. The applicability of the abnormality criterion to these improved estimates is reviewed.…

Four bootstrap methods are identified for constructing confidence intervals for the binomial-error model. The extent to which similar results are obtained and the theoretical foundation of each method and its relevance and ranges of modeling the true score uncertainty are discussed. (SLD)

Formulas are provided for estimating the reliability of a linear composite of non-equivalent subtests given the reliabilities of component subtests. The reliability of the composite is compared to that of its components. An empirical example uses data from 170 children aged 4 through 8 years performing 34 Piagetian tasks. (SLD)

A method is proposed for sequential evaluation of reliability of psychometric instruments. Sample size is unfixed; a test statistic is computed after each person is sampled and a decision is made in each stage of the sampling process. Results from a series of Monte-Carlo experiments establish the method's efficiency. (SLD)

Two attempts to adjust state mean Scholastic Aptitude Test (SAT) scores for differential participation rates are examined. Both attempts are rejected, and five rules for performing adjustments are outlined to foster follow-up checks on untested assumptions. National Assessment of Educational Progress state data are determined to be more accurate.…

Three correlation matrices (PEARSON, POLYCHORIC, and TOBIT) were used to obtain reliability estimates on ordered polytomous variable models. A Monte Carlo study with different levels of variable asymmetry and 400 sample correlation matrices demonstrated that the PEARSON matrix did not perform as well as did the other 2 matrices. (SLD)

This paper discusses standard error of measurement (SEM), the amount of variation or spread in the measurement errors for a test, and gives information needed to interpret test scores using SEMs. SEMs at various score levels should be used in calculating score bands rather than a single SEM value. (SLD)