Large-scale language testing uses statistical information to account for the quality of an assessment system. In this reflection article, I explain how basic statistics can be used meaningfully in the context of classroom language assessment. The paper explores a series of statistical calculations that can be used to examine test scores and…

Fifty years ago, Robert Glaser introduced the concept of criterion-referenced measurement in an article in American Psychologist. Its early proponents predicted that this measurement strategy would revolutionize education. But has it lived up to its promise? W. James Popham explores this question by looking at the history of criterion-referenced…

In adolescence research, the treatment of measurement reliability is often fragmented, and it is not always clear how different reliability coefficients are related. We show that generalizability theory (G-theory) is a comprehensive framework of measurement reliability, encompassing all other reliability methods (e.g., Pearson "r,"…

The assessment of young children in early childhood special education is a central area of educational practice. The results of child assessments often have significant implications for young children, their families, and the programs that serve them, including eligibility for special education services, instructional planning, and documentation…

Techniques for classifying individuals into mastery or non-mastery status based on criterion-referenced test performance are investigated. Extensions of mastery classification techniques developed by Macready and Dayton are presented. The techniques are based on latent class and quasi-independence models. (Author/JKS)

Addresses the issue of counselor expertise in test interpretation. Discusses norm-referenced versus criterion-referenced interpretation, interpreting the precision of the information, interpreting the meaning of the construct and its relevance to the decision, and general precautions regarding test interpretation. (LLL)

In keeping with the theme of the International Language Testing Association/Language Testing Research Colloquium Conference in 2008, "Focusing on the Core: Justifying the Use of Language Assessments to Stakeholders," I define "stakeholder-friendly tests," "defensible testing," and "testing-context analysis."…

When comparing examinees to a control group or person, the examiner usually does not know the probability of correct classification based on the number of items used and the number of people tested. Using ranking and selection techniques, a framework is described for deriving a lower bound on this probability. (Author/JKS)

Criterion-referencing is a way to enhance the interpretation of test scores by referencing them to well-defined behavior domains. Behavior domains may be ordered or unordered; several varieties of criterion-referenced tests within each of these types are discussed. (Author/RL)

To realize the dividends from the relationship between testing and teaching, teacher and administrator preparation and inservice training must be redesigned so that professionals are equipped to interpret results from norm-referenced and criterion-referenced tests designed by experts. (JOW)

A defense of the use of standards with criterion-referenced testing is made in response to Glass's article (TM 504 031). (JKS)

Examines the extent to which grades derived from a conventional norm-referenced examination can be interpreted in terms of criterion-referenced performance assessments of different abilities and skills. Results suggest that performance is more affected by test format and subject matter than by the intellectual abilities tested by them. (JOW)

Standards-based score reports interpret test performance with reference to cut scores defining categories like "below basic," "proficient," or "master." This article first develops a conceptual framework for validity arguments supporting such interpretations, then presents three applications. Two of these serve to introduce new standard-setting…

The use of setting standards for criterion-referenced tests is defended in a response to two papers by Gene Glass and Nancy Burton. (JKS)

The problem of determining an optimal passing score for a mastery test is discussed, when the purpose of the test is to predict success on an external criterion. For the case of constant losses for the two possible error types, a method for determining passing scores is derived. (Author/JKS)