In equating research and practice, equating functions that are smooth are typically assumed to be more accurate than equating functions with irregularities. This assumption presumes that population test score distributions are relatively smooth. In this study, two examples were used to reconsider common beliefs about smoothing and equating. The…

Utilizing disaggregated data from the Office of the Superintendent of Public Instruction (OSPI) and the Educational Research Data Center (ERDC), this report offers a deeper and more nuanced perspective on the educational realities of Asian Americans and Pacific Islander (AAPI) students and reinforces the need for disaggregated data to unmask the…

The study evaluated the effectiveness of log-linear presmoothing (Holland & Thayer, 1987) on the accuracy of small sample chained equipercentile equatings under two conditions (i.e., using small samples that differed randomly in ability from the target population "versus" using small samples that were distinctly different from the…

Recently, there has been an increasing level of interest in subscores for their potential diagnostic value. Haberman (2008) suggested a method based on classical test theory to determine whether subscores have added value over total scores. This paper provides a literature review and reports when subscores were found to have added value for…

In 2013, the National Commission on Asian American and Pacific Islander Research in Education (CARE) and the White House Initiative on Asian Americans and Pacific Islanders (WHIAAPI)--with support from ETS and Asian Americans and Pacific Islanders in Philanthropy (AAPIP)--began an Asian American and Pacific Islander (AAPI) data quality campaign.…

Large-scale educational surveys are low-stakes assessments of educational outcomes conducted using nationally representative samples. In these surveys, students do not receive individual scores, and the outcome of the assessment is inconsequential for respondents. The low-stakes nature of these surveys, as well as variations in average performance…

This study compared the accuracies of four differential item functioning (DIF) estimation methods, where each method makes use of only one of the following: raw data, logistic regression, loglinear models, or kernel smoothing. The major focus was on the estimation strategies' potential for estimating score-level, conditional DIF. A secondary focus…

A general diagnostic model was used to specify and compare two multidimensional item-response-theory (MIRT) models for longitudinal data: (a) a model that handles repeated measurements as multiple, correlated variables over time (Andersen, 1985) and (b) a model that assumes one common variable over time and additional orthogonal variables that…

This document describes the breadth of the research that the ETS (Educational Testing Service) Research & Development division is conducting in 2010. This portfolio will be updated in early 2011 to reflect changes to existing projects and new projects that were added after this document was completed. The research described in this portfolio falls…

This document describes the breadth of the research being conducted in 2008 by the Research and Development Division at Educational Testing Service (ETS). The research described falls into three large categories: (1) Research supported by the ETS research allocation; (2) Research funded by testing programs at ETS; and (3) Research funded by…