Generalized Likelihood Tests for Sequentially Monitoring Drift in Response and Response-Time Model Parameters

• In Event: AERA Poster Session 6
  In Poster Session: Division D Section 1 Poster Session 2

Abstract

The study investigates statistical procedures for sequentially monitoring the quality of items in continuous testing. The study proposes two types of online monitoring algorithms and verifies their performance in computerized adaptive testing (CAT). To evaluate the effectiveness of the procedures, the study conducts extensive simulations and applies the suggested methods to large-scale operational test data.

Author

• Hyeon-Ah Kang, The University of Texas at Austin