We examined how much agreement there was between scores from large-scale mandated assessments and report-card grades for 14,776 students in grades 3, 6, and 9 of a district in which conditions were conducive to alignment of assessments. We found significant mean differences between internal and external assessments: effect sizes were 0.29 to 0.63…

Four-year colleges and universities submit faculty teaching load and instructional cost data annually to the Delaware Study of Instructional Costs and Productivity. While the Delaware Study currently adjusts the calculation of annual FTE students to account for the difference in annual student credit hours (SCH) earned by students at semester and…

This paper studies whether equating results can be improved if the variable that accounts for all systematic differences between equating populations is identified and used as an anchor in anchor test design or as a variable on which to match equating samples. The sample invariant properties of four anchor test equating methods (Tucker and Levine…

This research derives simplified formulas for computing the standard error of the frequency estimation method for equating score distributions that are continuized using a uniform or Gaussian kernel function (P. W. Holland, B. F. King, and D. T. Thayer, 1989; Holland and Thayer, 1987). The simplified formulas are applicable to equating both the…

This study investigates the population sensitivity of the commonly used linear equating methods in the Non-Equivalent-groups with an Anchor Test (NEAT) design: the Tucker, the Levine observed-score, and the chain linear methods. For a detailed analysis of the subject, we apply three distinctive approaches to a real data set from a NEAT design: a)…

There are test-equating situations in which it may be appropriate to fit a loglinear or other type of probability model to the joint distribution of a total score on a test and a score on part of that test. For anchor test designs, this situation arises for internal anchor tests, which are embedded within the total test. Similarly, a part-whole…

Conventional linear and equipercentile procedures are reviewed with an emphasis on their utility for equating achievement tests pitched at different levels of difficulty. It is argued that the equipercentile procedure is superior to the linear procedure, but that neither is very satisfactory for the vertical equating problem. (Author/JKS)

An analytic procedure for smoothing in equipercentile equating using cubic smoothing splines is described and illustrated. The effectiveness of the procedure is judged by comparing the results from smoothed equipercentile equating with those from other equating methods using multiple cross-validations for a variety of sample sizes. (Author/JKS)

The metric of the multidimensional item response theory (MIRT) item parameter estimates is usually referred to as reference axes that are orthogonal and of unit length. This is due to the fact that most MIRT parameter estimation programs solve the identification problem by requiring that multidimensional abilities be distributed as multivariate…

Item response theory (IRT) item parameters can be estimated using data from a common item equating design either separately for each form or concurrently across forms. This paper reports the results of a simulation study of separate versus concurrent item parameter estimation. Using simulated data from a test with 60 dichotomous items, 4 factors…

The functions, goals, and characteristics of test standardization are discussed, including an explanation of how score equating as an aspect of standardization is essential to the achievement of equity in testing. Psychometric specialists and testing program directors must understand score equating to ensure equitable use of tests. (Author/AL)

Presents 17 rules of thumb to create surveys that are likely to provide data of high enough quality to meet the requirements for measurement specified in a probabilistic conjoint measurement model. Use of these steps should allow the survey to be joined with others measuring the same variable to ensure continued equating with a single reference…

Studied the degree to which equating functions failed to demonstrate population invariance across subpopulations, using two root-mean-square difference measures of the degree to which functions used to link two tests computed on subpopulations differ from the linking function for the whole population. Illustrated the ideas using data from the…

Examined the effect of test purification in detecting differential item functioning (DIF) by means of polytomous extensions of the Raju area measures (N. Raju, 1990) and the Lord statistic (F. Lord, 1980). Simulation results suggest the necessity of using a two-stage equating purification process with the Raju exact measures and the Lord statistic…

A new report, "The Proficiency Illusion," released last year by the Thomas B. Fordham Institute states that the tests that states use to measure academic progress under the No Child Left Behind Act (NCLB) are creating a false impression of success, especially in reading and especially in the early grades. The report is a collaboration…