Validity and Test Length Reduction Strategies for Complex Assessments

• In Event: Rasch Modeling: Methodology and Application

Abstract

Lengthy standardized assessments decrease instructional time while increasing concerns about student cognitive fatigue. This study explores five item-reduction methods to reduce the number of items on a mathematical problem-solving assessment for sixth-grade students. Each shortened instrument was evaluated through test content, internal structure, and relationships to other variables. The two statistical methods (Rasch model and point-biserial) resulted in the best performing shortened assessments, while the three qualitative (content preservation) methods resulted in poorly performing assessments. Implications for the study provide a methodological framework for researchers to use to reduce the length of existing instruments while demonstrating sufficient validity evidence.

Authors

• Lance Kruse, North Carolina State University

• Gregory Stone

• Toni A. May (Sondergeld), Drexel University

• Jonathan David Bostic, Bowling Green State University