The population discrepancy between unstandardized and standardized reliability of homogeneous multicomponent measuring instruments is examined. Within a latent variable modeling framework, it is shown that the standardized reliability coefficient for unidimensional scales can be markedly higher than the corresponding unstandardized reliability…

This note confronts the common use of a single coefficient alpha as an index informing about reliability of a multicomponent measurement instrument in a heterogeneous population. Two or more alpha coefficients could instead be meaningfully associated with a given instrument in finite mixture settings, and this may be increasingly more likely the…

As the use of diagnostic assessment systems transitions from research applications to large-scale assessments for accountability purposes, reliability methods that provide evidence at each level of reporting are needed. The purpose of this paper is to summarize one simulation-based method for estimating and reporting reliability for an…

The Mathematics Fluency and Calculation Tests (MFaCTs) are a series of measures designed to assess for arithmetic calculation skills and calculation fluency in children ages 6 through 18. There are five main purposes of the MFaCTs: (1) identifying students who are behind in basic math fact automaticity; (2) evaluating possible delays in arithmetic…

Houston's experience with the Educational Value-Added Assessment System (R) (EVAAS) raises questions that other districts should consider before buying the software and using it for high-stakes decisions. Researchers found that teachers in Houston, all of whom were under the EVAAS gun, but who taught relatively more racial minority students,…

Researchers often argue that the structural models of the constructs they study are relevant to clinicians. Unfortunately, few clinicians are able to translate the mathematically precise relationships between latent constructs and observed scores into information that can be usefully applied to individuals. Typically this means that when a new…

This paper discusses the issues involved in calculating indices of composite reliability for "modular" or "unitised" assessments of the kind used in GCSEs, AS and A level examinations in England. The increasingly widespread use of on-screen marking has meant that the item-level data required for calculating indices of…

One of the problems inherent in variance component estimation centers around inadmissible estimates. Such estimates occur when there is more variability within groups, relative to between groups. This paper suggests a Bayesian approach to resolve inadmissibility by placing noninformative inverse-gamma priors on the variance components, and…

Despite questions about validity and reliability, the use of value-added estimation methods has moved beyond academic research into state accountability systems for teachers, schools, and teacher preparation programs (TPPs). Prior studies of value-added measurement for TPPs test the validity of researcher-designed models and find that measuring…

This study examined the reliability, validity, and predictive utility of kindergarten screening for risk for math difficulty (MD). Three screening measures, administered in September and May of kindergarten to 196 students, assessed number sense and computational fluency. Conceptual and procedural outcomes were measured at end of first grade, with…

The relationship between stratified alpha (alpha-sub(s)) and the reliability of a test composed of interrelated nonhomogeneous items is examined. It is mathematically demonstrated that when there is congeneric equivalence within the strata or subtests, the difference between the coefficients is a function of the variances of the loadings within…

Raju and Oshima (2005) proposed two prophecy formulas based on item response theory in order to predict the reliability of ability estimates for a test after change in its length. The first prophecy formula is equivalent to the classical Spearman-Brown prophecy formula. The second prophecy formula is misleading because of an underlying false…

In this paper, formulas for computing the weights that maximize the reliability of a test with multiple parts are derived using a congeneric model. A direct derivation for the three-part test and case and a two-step derivation for the n-part case are presented, and results for these two approaches are shown to be consistent for the three-part…

The authors evaluate Angrist and Krueger (1991) and Bound, Jaeger, and Baker (1995) by constructing reliable confidence regions around the 2SLS and LIML estimators for returns-to-schooling regardless of the quality of the instruments. The results indicate that the returns-to-schooling were between 8 and 25 percent in 1970 and between 4 and 14…

To meet the requirements of the No Child Left Behind Act, school districts and states must compile summary reports of the levels of student achievement in reading and mathematics. The levels are to be described in broad categories: "basic and below," "proficient," or "advanced." Educational units are given considerable latitude in defining the…