Analyzing Student Response Processes to Evaluate Success on a Technology-Based Problem-Solving Task
Yuting Han, Mark Wilson
Abstract
A technology-based problem-solving test can automatically capture all the actions of students when they complete tasks and save them as process data. Response sequences are the external manifestations of the latent intellectual activities of the students, and it contains rich information about students’ abilities and different problem-solving strategies. This study adopted the mixture Rasch measurement models (MRMs) in analyzing the success of technology-based tasks while automatically classifying the different response patterns based on the characteristics of the response process. The Olive Oil task from the Assessment and Teaching of 21st Century Skills project (ATC21S) is taken as an example to illustrate the use of MRMs and the interpretation of the process data.