Economists often use test scores to measure a student's performance or an adult's human capital. These scores reflect non-trivial decisions about how to measure and scale student achievement, with important implications for secondary analyses. For example, the scores computed in several major testing regimes, including the National Assessment of…

GMAT (Graduate Management Admission Test) scaled scores convey the same level of ability over time, and GMAT percentiles convey the competitiveness of scores relative to today's GMAT test takers. In an earlier column, the author discussed the role of the GMAT scaled scores and percentiles. Here, he gets more technical and discusses how GMAT scaled…

This paper illustrates that the psychometric properties of scores and scales that are used with mixed-format educational tests can impact the use and interpretation of the scores that are reported to examinees. Psychometric properties that include reliability and conditional standard errors of measurement are considered in this paper. The focus is…

A grade-reference curve (GRC) can be constructed for any course based on the grades of a course in the last several years. Among other things, the reference curve of a course can be used to test for any abnormality in the current semester's grades of a course. It can be a very important document about the course that serves students, teachers and…

The purpose of the Test for English Majors (TEM) is to measure the English proficiency of Chinese university undergraduates majoring in English Language and Literature and to examine whether these students meet the required levels of English language abilities as specified in the National College English Teaching Syllabus for English Majors…

"Scaling" is the process of constructing a score scale that associates numbers or other ordered indicators with the performance of examinees. Scaling typically is conducted to aid users in interpreting test results. This module describes different types of raw scores and scale scores, illustrates how to incorporate various sources of…

The graded response (GR) and generalized partial credit (GPC) models do not imply that examinees ordered by raw observed score will necessarily be ordered on the expected value of the latent trait (OEL). Factors were manipulated to assess whether increased violations of OEL also produced increased Type I error rates in differential item…

Following an exploratory factor analysis, factor scores may be computed and used in subsequent analyses. Factor scores are composite variables which provide information about an individual's placement on the factor(s). This article discusses popular methods to create factor scores under two different classes: refined and non-refined. Strengths and…

We believe a lack of transparency undermines both the credibility of, and interest in, stated choice studies among policy makers. Unlike articles reporting the results of contingent valuation studies, papers in the stated choice literature rarely present simple tabulations of raw response data (that is, a table or graph showing the percentage of…

A theoretical advantage of item response theory (IRT) models is that trait estimates based on these models provide more test information than any other type of test score. It is still unclear, however, whether using IRT trait estimates improves external validity results in comparison with the results that can be obtained by using simple raw…

Describes the steps for estimating a population mean from three test items from a test that has been calibrated. Because the Rasch model allows for a direct transformation between raw scores and logit measures, if a population mean in logits is known relative to a set of item calibrations, the population mean in raw score units can be determined.…

Provides a comprehensive and integrated treatment of both conditional absolute standard errors of measurement (SEM) and conditional relative SEMs from the perspective of generalizability theory. Illustrates the approach with examples from commercial standardized tests. Examples support the conclusion that both types of conditional SEMs tend to be…

This study demonstrates how mixture distribution item response models can be used to detect different response styles in the clinical assessment of anger expression. Analyses of 3 subscales of the State-Trait Anger Expression Inventory in a clinical sample of 4,497 patients revealed that there are different response styles that manifest themselves…

Something new is on the horizon, and depending on one's role on campus, it might be storm clouds or a cleansing shower. Either way, no matter how hard one tries to avoid it, sooner rather than later he/she will have to deal with metrics. Metrics do not have to cause fear and resistance. Metrics can, and should, be a powerful tool for improvement.…

In comparing measurement theories, it is evident that the awareness of the concept of measurement error during the time of Galileo has lead to the formulation of observed scores comprising a true score and error (classical theory), universe score and various random error components (generalizability theory), or individual latent ability and error…