Quality control of statistical learning environments and prediction of learning outcomes through reproducible computing

This article introduces a new approach to statistics education that allows us to accurately measure and control key aspects of the computations and communication processes that are involved in non-rote learning within the pedagogical paradigm of Constructivism. The solution that is presented relies on a newly developed technology (hosted at www.freestatistics.org) and computing framework (hosted at www.wessa.net) that supports reproducibility and reusability of statistical research results that are presented in a so-called Compendium. Reproducible computing leads to responsible learning behaviour, and a stream of high-quality communications that emerges when students are engaged in peer review activities. More importantly, the proposed solution provides a series of objective measurements of actual learning processes that are otherwise unobservable. A comparison between actual and reported data, demonstrates that reported learning process measurements are highly misleading in unexpected ways. However, reproducible computing and objective measurements of actual learning behaviour, reveal important guidelines that allow us to improve the effectiveness of learning and the e-learning system.

Publication year:2009

BOF-keylabel:yes

IOF-keylabel:yes

BOF-publication weight:0.5

CSS-citation score:1

Authors from:Higher Education