The Accurate Measurement of Students’ Learning in E-Learning Environments

Abstract

The ultimate goal of E-learning environments is to improve students’ learning. To achieve that goal, it is crucial to accurately measure students’ learning. In the field of educational measurement, it is well known that the key issue in the measurement of learning is to place test scores on a common metric. Despite the crucial role of a common metric in the measurement of learning, however, less attention has been paid to this important issue in E-learning studies. In this study, we propose to use fixed-parameter calibration (FPC) in an item response theory (IRT) framework to set up a common metric in E-learning environments. To demonstrate FPC, we used the data from the MOOC “Introduction to Psychology as a Science” offered through Coursera collaboratively by Georgia Institute of Technology (GIT) and Carnegie Mellon University (CMU) in 2013. Our analysis showed that the students’ learning gains were substantially different with and without FPC.

Keywords

• massive open online courses
• equating
• common metric
• fixed-parameter calibration
• item response theory