Comparison of Learning Outcomes for Simulation-based and Traditional Inference Curricula in a Designed Educational Experiment

Abstract

The focus of the following study is to make a formal comparison of learning outcomes under the traditional and simulation-based inference curricula. The learning outcomes for concepts surrounding inference with confidence intervals and hypothesis testing are of primary interest. A randomized experiment was conducted to administer the two curricula to students in an in- troductory statistics course. The experimental design allows for causal inference to be drawn about the effect of curriculum type on the learning outcomes. The results indicate that signifi- cant improvement in learning outcomes for confidence interval related topics are achieved using the simulation-based teaching methods.