September 1, 1998
Problem Choice by Test Takers: Implications for Comparability and Construct Validity
Authors:
Robert L. Linn, Damian W. Betebenner, and Kerry S. Wheeler
In this study, researchers analyzed results from extended response items on the Oregon State Assessment. Students were able to select one of two extended response problems. The researchers found that the two problems differed in popularity and that the student scores differed as a function of their choice. They concluded that while choice may be justified, some form of equating adjustments would be necessary before making high-stakes decisions on student performance.
Linn, R. L., Betebenner, D. W., & Wheeler, K. S. (1998). Problem choice by test takers: Implications for comparability and construct validity (CSE Report 485). Los Angeles: University of California, Los Angeles, National Center for Research on Evaluation, Standards, and Student Testing (CRESST).