Fraud Detection in Statistics Education Based on the Compendium Platform and Reproducible Computing

Wessa, Patrick; Baesens, Bart

doi:10.1109/csie.2009.710

Cited by 4 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent paper [33] shows how Reproducible Computing can be used to visualize and mathematically describe the interactions in Social Networks in which the students are related through the computations that are "borrowed" from each other. The reason why this is possible is the fact that the underlying technology captures all dependencies between computations: for instance, when someone reproduces a stored computation A and reuses it to create an improvement version B, then A becomes a parent of B (and B is a child of A).…”

Section: Social Network and Fraud Detectionmentioning

confidence: 99%

“…This results in a large number of parent-child relationships between the computations which can be unambiguously associated with individual students. If one uses a simple indexing software to list all the computational references (hyperlinks) of submitted student papers, and links this information with the database of the stored computations, then it is possible to create the so-called "sociogram" in which the process of borrowing (of ideas and computations) is displayed [33]. This does not only allow us to study social interaction between students (based on actual computations) but it also enables us to quickly detect free riding, data tampering, and obfuscation (of borrowed ideas) -something which is impossible with traditional fraud detection systems that focus exclusively on text-based plagiarism.…”

Section: Social Network and Fraud Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Reproducible Computing: a new Technology for Statistics Education and Educational Research

Wessa¹,

Ao²

2009

AIP Conference Proceedings

Self Cite

View full text Add to dashboard Cite

This paper explains how the R Framework (http : //www. wessa .net) and a newly developed Compendium Platform (http : //www. freestatistics. org) allow us to create, use, and maintain documents that contain empirical research results which can be recomputed and reused in derived work. It is illustrated that this technological innovation can be used to create educational applications that can be shown to support effective learning of statistics and associated analytical skills. It is explained how a Compendium can be created by anyone, without the need to understand the technicalities of scientific word processing (MgX) or statistical computing (R code). The propo&sd Reproducible Computing system allows educational researchers to objectively measure key aspects of the actual learning process based on individual and constructivist activities such as: peer review, collaboration in research, computational experimentation, etc. The system was implemented and tested in three statistics courses in which the use of Compendia was used to create an interactive e-leaming environment that simulated the real-world process of empirical scientific research.

show abstract

Section: Social Network and Fraud Detectionmentioning

confidence: 99%

Section: Social Network and Fraud Detectionmentioning

confidence: 99%

Reproducible Computing: a new Technology for Statistics Education and Educational Research

Wessa¹,

Ao²

2009

AIP Conference Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such documents can be easily created (even by students) and permit any reader to (exactly) recompute the statistical results that are presented therein. A few simple clicks are sufficient to have the R Framework reproduce the results and to reuse them in derived work [37]. The practical implications of this technology will become obvious in section 3 because the three figures that are presented can be recomputed and reused through the Compendium Platform.…”

Section: Compendium Platformmentioning

confidence: 99%

“…In a recent paper [37] it is illustrated how the Compendium Platform's repository supports "technical" quality control of the statistical software and accompanying documentation for students. On the one hand, reproducible computing allows students to accurately communicate computational problems and questions without the need to understand the underlying technicalities.…”

Section: Objective Measurements Versus Reported Datamentioning

confidence: 99%

“…The main reason for creating the R Framework and the Compendium Platform, is that it allows anyone to create and use Compendia of reproducible research. A Compendium is defined as [37]: a research document where each computation is referenced by a unique URL that points to an object that contains all the information that is necessary to recompute it. Such documents can be easily created (even by students) and permit any reader to (exactly) recompute the statistical results that are presented therein.…”

Section: Compendium Platformmentioning

confidence: 99%

See 1 more Smart Citation

Quality Control of Statistical Learning Environments and Prediction of Learning Outcomes through Reproducible Computing

Wessa

2009

INT J COMPUT COMMUN

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Does Reviewing Lead to Better Learning and Decision Making? Answers from a Randomized Stock Market Experiment

Wessa

Holliday

2012

PLoS ONE

Self Cite

View full text Add to dashboard Cite

BackgroundThe literature is not univocal about the effects of Peer Review (PR) within the context of constructivist learning. Due to the predominant focus on using PR as an assessment tool, rather than a constructivist learning activity, and because most studies implicitly assume that the benefits of PR are limited to the reviewee, little is known about the effects upon students who are required to review their peers. Much of the theoretical debate in the literature is focused on explaining how and why constructivist learning is beneficial. At the same time these discussions are marked by an underlying presupposition of a causal relationship between reviewing and deep learning.ObjectivesThe purpose of the study is to investigate whether the writing of PR feedback causes students to benefit in terms of: perceived utility about statistics, actual use of statistics, better understanding of statistical concepts and associated methods, changed attitudes towards market risks, and outcomes of decisions that were made.MethodsWe conducted a randomized experiment, assigning students randomly to receive PR or non–PR treatments and used two cohorts with a different time span. The paper discusses the experimental design and all the software components that we used to support the learning process: Reproducible Computing technology which allows students to reproduce or re–use statistical results from peers, Collaborative PR, and an AI–enhanced Stock Market Engine.ResultsThe results establish that the writing of PR feedback messages causes students to experience benefits in terms of Behavior, Non–Rote Learning, and Attitudes, provided the sequence of PR activities are maintained for a period that is sufficiently long.

show abstract

Fraud Detection in Statistics Education Based on the Compendium Platform and Reproducible Computing

Abstract: This paper focuses on a newly developed method to detect fraud in empirical papers that are submitted by students. The proposed solution is based

Cited by 4 publications

References 10 publications

Reproducible Computing: a new Technology for Statistics Education and Educational Research

Reproducible Computing: a new Technology for Statistics Education and Educational Research

Quality Control of Statistical Learning Environments and Prediction of Learning Outcomes through Reproducible Computing

Does Reviewing Lead to Better Learning and Decision Making? Answers from a Randomized Stock Market Experiment

Contact Info

Product

Resources

About