Journal of Educational and Behavioral Statistics | 2019
Introduction to the Special Issue on Research and Development on Large-Scale Educational Assessment Programs
Abstract
In 1992, the Journal of Educational Statistics (just before the name change to Journal of Educational and Behavioral Statistics [JEBS]) published a special issue pertaining to the statistical and measurement issues inherent in the last major round of redesign of the National Assessment of Educational Progress (NAEP). That special issue, guest-edited by Rebecca Zwick, proved to be seminal. It explained and familiarized the methodological community with core design features that NAEP had pioneered: the use of randomization in the sampling of items, the imputation of plausible values for consistent population inference, and the integration of item response modeling with latent regression models, to name just a few. It motivated several generations of methodologists and substantive researchers to use and to improve upon the NAEP design and analysis principles in their own work. Two years ago, a full quarter century since the publication of the NAEP special issue, it became apparent to JEBS and the large-scale assessment community that much new development had taken place and a new special issue was warranted. A proposal with a list of chapters was generated and reviewed by the JEBS Management Committee. Potential chapter authors were invited, and I felt fortunate that there was strong commitment to participation from frontline researchers overseeing or carrying out the research and development. Summarizing the five chapters in this special issue is a daunting task, but there are at least two significant developmental trends worth noting. The first is the infusion of educational technology into the assessment experience. This change has led to vexing methodological questions (Chapters 1 and 2) but also significant new opportunities (Chapter 3). The second trend is the proliferation of NAEP-inspired principles in other large-scale educational assessment programs with global significance. Offering examples, Chapter 4 introduces readers to efforts in measuring the quality of educational systems in such a vast country as China, and Chapter 5 provides an overview of the methodologies behind making international comparisons. The following individuals reviewed one or more draft chapters in this special issue: Dan Bolt, Ping Chen, Christine DeMars, Paul De Boeck, Jean-Paul Fox, Ed Haertel, Andrew Ho, Roy Levy, Tracy Sweet, Matthias von Davier, Chun Wang, Tao Xin, and Rebecca Zwick. To them, I am indebted. I also owe special gratitude to Lauren Harrell who not only reviewed many of the chapters but also provided much impetus and feedback. Any omissions or editorial oversights are mine. Journal of Educational and Behavioral Statistics 2019, Vol. 44, No. 6, pp. 647 DOI: 10.3102/1076998619887740 Article reuse guidelines: sagepub.com/journals-permissions © 2019 AERA. http://jebs.aera.net