The Impact of Item Difficulty Drift on Pre-Equated Assessments

• In Event: 41.083 - Roundtable Session 15
  In Roundtable Session: 41.083-17 - Roundtable: Examining Construct-Irrelevant Factors Impacting Test Score Interpretations in Statewide Assessments

Abstract

The use of pre-equated item parameters and resulting scale scores are becoming more prevalent in large scale assessments. In these tests, decisions are needed for when, and if, item parameters should be recalibrated to maintain the validity of the student score interpretations. This study was performed on a brief, static, ELL placement test, initially calibrated with less than 700 students, and is currently in the process of being refreshed after four years of use. The study addresses whether there has been item difficulty drift since the initial calibration, and if drift is observed, whether the operational set should be recalibrated prior to estimating the parameters of the new items and how that recalibration might affect student scale scores.

Author

• Lietta M. Scott, Arizona Department of Education