Experiment Replication and Meta-Analysis in Evaluation of Intelligent Tutoring System’s Effectiveness

This paper presents the methodology for conducting controlled experiment replication, as well as, the results of a controlled experiment and an internal replication that investigated the effectiveness of an intelligent tutoring system. Since, there doesn’t seem to be a common ground on guidelines for the replication of experiments in intelligent tutoring system’s educational influence evaluation, this scientific method has just started to be applied to this propulsive research field. We believe that every effectiveness evaluation should be replicated at least in order to verify the original results and to indicate an evaluated e-learning system’s advantages or disadvantages. On the grounds of experiment replication, a meta-analysis can be conducted in order to calculate overall intelligent tutoring system effectiveness. Key-Words: e-learning, intelligent tutoring systems, evaluation, effect size, effectiveness, experiment, replication, meta-analysis