Are all biases bad? Collaborative grounded theory in developmental evaluation of education policy
The major purpose of this paper is to investigate the effects of CAT test design and bank distribution on the content coverage and the efficiency of the tests.
Topics: Test design, Computer adaptive testing, Learning standards & alignment
A large-scale, long-term study of scale drift: The micro view and the macro view
This study examined the measurement stability of a set of Rasch measurement scales that have been in place for almost 40 years.
Rapid‐guessing behavior: Its identification, interpretation, and implications
The rise of computer‐based testing has brought with it the capability to measure more aspects of a test event than simply the answers selected or constructed by the test taker. One behavior that has drawn much research interest is the time test takers spend responding to individual multiple‐choice items.
Topics: Measurement & scaling, Innovations in reporting & assessment, School & test engagement
Using a nationally representative dataset with thousands of measures, I employ data reduction techniques to identify a handful of variables that are the strongest predictors of college readiness and understand what they measure.
This article addresses the issue by estimating teacher value added, then applying extremely mild nonlinear transformations to the original scale and re-estimating the value added. Although by definition at most one of these scales can be equal-interval, all are treated as if interval-scaled when estimating value added.
Topics: Measurement & scaling, Student growth & accountability policies
This article details the early kindergarten transition (EKT) program evaluation study conducted by a university–district partnership, as well as testimony from district leadership on the utility of the research deliverables and the longterm benefits of the research collaboration.
Topics: Empowering educators
