Response Latencies and Ability Estimation in Computer Adaptive Assessment: A Modified Algorithm

Περίληψη

Computer-based assessment has been used around the world to generate feedback and quantify pupils’ learning or knowledge. Pupils’ learning may be evaluated by studying the accuracy of their responses but much information may be unearthed by considering their response latencies (response time). This study proposes a new Item Response Theory algorithm for the estimation of the ‘ability parameter ’ of pupils in the context of a computer adaptive testing system. The algorithm weights less the responses that are given too soon after the stimuli are presented, so they may not be considered as legitimate and honest efforts for a correct response. The application of the algorithm on empirical data (N=920) in the context of the mathematics National Curriculum in England gave indications of increased validity and usefulness of test results. The consequences on the classroom teaching and assessment routine are discussed.