The StatPlay principals, to whom enquiries should be directed, are Geoff Cumming (G.Cumming@latrobe.edu.au) and Neil Thomason(n.thomason@hps.unimelb.edu.au). We did not achieve commercialisation of StatPlay.

What is StatPlay? StatPlay is interactive multimedia to support understanding of some key concepts of the foundation statistics course. It offers vivid graphical representations of concepts and, in many cases, multiple representations that are dynamically linked. It is written in Visual C++ to run under Windows. There are printed worksheets designed to guide exploitation of StatPlay to support learning. StatPlay emphasises interactivity and exploration, and offers students take-home images of statistical concepts.

StatPlay development. StatPlay was developed during 1994-1999, with major funding from the University of Melbourne and CAUT-CUTSD. Chief software developers were Jan Les, Mark Zangari and Jack Zhang. Sue Finch (design, materials, research) and Robert Maillardet (design, statistics, management) were key team members. Kevin Korb of Monash University joined the project in 1999.

StatPlay in use. StatPlay has been used at La Trobe University since 1995 and the University of Melbourne since 1997, where it has been used at various times in over 12 departments with up to 3,500 students in a year. StatPlay and its use have been described in many publications.

StatPlay versions

StatPlay Classic
This is the original StatPlay, developed during 1994-1997 to run under Windows 3.11. It includes Sam (as in ‘Play it again…’), which is a facility for recording, storing and playing back multimedia ‘demos’. There is a set of stored demos that are referred to in the Classic workbook ‘All about StatPlay’: The worksheets guide students working with StatPlay, and invite students to play back demos frequently to illustrate concepts and guide their work. It is StatPlay Classic that has been, and is, in classroom use. It is moderately robust and debugged, but some glitches remain. Sam is a wonderful feature: It is very easy to record your own demos.

StatPlay 1.0 (release 23)
Developed from 1997-1999, to run under Windows 95, this version has a much-improved, customised interface. Each playground has an expanded range of features. This is the version that was intended for development for commercial publication. Development ceased, unfortunately, when a plan for major investment to fund completion and worldwide marketing fell through at the last minute in late 1999. This version is incomplete, with its playgrounds in various stages of development. Some have glitches. Sam recording is not available, but a small number of demos are included and may be played back, to guide exploration.

Publications describing StatPlay and its use

A recent overview:

Cumming, G., & Thomason, N. (1998). StatPlay: Multimedia for statistical understanding. In L. Pereira-Mendoza, L. Kea, T. Kee, & W-K. Wong (Eds.) Statistical education: Expanding the network. Proceedings of the Fifth International Conference on Teaching of Statistics (pp. 947-952). Voorburg, The Netherlands: International Statistical Institute. (ISBN 9073592-14-3)

Abstract:
StatPlay is multimedia for conceptual understanding in the introductory statistics course in any discipline. Its aim is to help overcome misconceptions about fundamental statistical concepts, and thus improve education and promote highly desirable reform of statistical practice by researchers in the social and behavioural sciences. StatPlay comprises simulations and tools in a number of microworlds in the broad areas of distributions, data, sampling, estimation and statistical significance testing. StatPlay design strategies include provision of vivid take-home images of concepts, multiple images of concepts dynamically linked, a high degree of interactivity, and a facility for the recording and playback of multimedia demonstrations. Classroom experience with StatPlay has been very positive, and commercialisation is now being sought.

Assessment of outcomes:

Finch, S., & Cumming, G. (1998). Assessing conceptual change in learning statistics. In L. Pereira-Mendoza, L. Kea, T. Kee, & W-K. Wong (Eds.) Statistical education: Expanding the network. Proceedings of the Fifth International Conference on Teaching of Statistics (pp. 897-903). Voorburg, The Netherlands: International Statistical Institute. (ISBN 9073592-14-3)

Abstract:
StatPlay, our multimedia for introductory statistics, aims to promote understanding of fundamental concepts. We describe assessment of students’ use of StatPlay’s Sampling Playground for learning about sampling variability, standard error and sampling distributions. Students worked with StatPlay’s interactive simulations, and undertook a range of prediction, estimation, labelling and explanation tasks. Results suggest that StatPlay’s striking visual representations can promote good understanding of sampling variability, and that confrontation with prior misconceptions and experience with the results of repeated sampling can be valuable, in particular, for understanding standard error.

Sam, the multimedia recording and playback tool

Les, J., Thomason, N., & Cumming, G. (1997). Play it again SAM: StatPlay and a recording and playback facility to support learning. In B. du Boulay & R. Mizoguchi (Eds.), Artificial intelligence in education (pp. 466-473). Amsterdam: IOS Press. (ISBN 90 5199 353 6)

Abstract:
StatPlay is our learning environment comprising illustrations and interactive simulations to assist learners understand some fundamental concepts of statistics. SAM is a facility that allows the recording, storage and playback of any sequence of interactions with StatPlay, together with a spoken commentary. SAM recordings, termed ‘demos’, can be used in a variety of ways to provide teacher explanations, examples and guidance for learners. Students can design and record a demo as a learning activity or an assessment task. Recordings can be made of teacher-learner, or learner-learner interactions and made available for future learners. Our aim is to investigate the educational value of augmenting a learning environment with such a simple facility, which draws on no sophisticated knowledge-based techniques. Early experience with SAM is promising.

The original description of the rationale for StatPlay’s design

Thomason, N., Cumming, G., & Zangari, M. (1994). Understanding central concepts of statistics and experimental design in the social sciences. In K. Beattie, C. McNaught & S. Wills (Eds.), Interactive multimedia in university education: Designing for change in teaching & learning (pp. 59-81, and subject of commentary pp. 99-102). Amsterdam: Elsevier.

Abstract:
We describe StatPlay, a collection of simulations intended to help students overcome their ‘Naive Statistics’ beliefs, i.e. common misconceptions of probability and statistics. ‘Naive Physics’ refers to misconceptions of elementary physics that many people show in their everyday behaviour: believing for example that a force is necessary to sustain motion. These misconceptions are often resistant to traditional education, but interactive use of computer simulations seems a promising way to promote true conceptual change. Correspondingly, we use the term ‘Naive Statistics’ to refer to misconceptions of probability, such as the ‘Law of Small Numbers’, and erroneous beliefs about statistical significance testing and other aspects of statistics. There is strong evidence that such erroneous conceptions are widely held, resistant to formal education, and have severely damaging consequences for research. Noting the promise of simulations for achieving conceptual change in physics, we are investigating simulations to help students build accurate concepts of some central aspects of statistics, probability and experimental design. StatPlay, our collection of demonstrations and interactive simulations, is being developed in Visual C++ for the Windows environment, and is at an early stage of development. In this paper we develop the rationale for the project and describe the facilities StatPlay provides for building conceptions about some statistical distributions and their properties, and about sampling.