STEPS TLTP Project

STatistical Education through Problem Solving:

The STEPS Project

Background and Philosophy

In 1992, the four UK Higher Education Funding bodies set up the Teaching and Learning Technology Programme (TLTP). The majority of the projects funded under this scheme were subject-based national consortia, aiming to use modern authoring tools to develop computer-based teaching materials.

The STEPS project brought together nine departments in seven universities throughout the UK to develop problem-based teaching and learning materials for statistics. In all, thirty or so academic statisticians and programmers helped to develop the STEPS materials.

The materials produced are based around specific problems arising in Biology, Business, Geography and Psychology. It is intended that students will discover that statistical issues arise from these problems as important natural parts of the process of reaching conclusions. The role of the computer is to assist in the exploration of the problem and to provide support materials for the statistical ideas encountered.

Graphical illustration plays a major role. A glossary of statistical terms is provided, and, where appropriate, problem modules can be operated in parallel with standard packages.

The funding for the STEPS project came to an end at the close of 1995, and in all, 38 teaching modules were produced and are now available: 37 for the PC, and 1 for the Mac. (Originally it was the intention to make the majority of the STEPS materials available for both PC and Mac; however a survey undertaken by the STEPS consortium revealed very little interest in STEPS material for the Mac, and most of the effort was therefore concentrated on the PC.)

The STEPS modules are intended to be used as problem-based lab material, to support existing coursework. The modules are not intended to replace lecturing staff or to provide a self-study course in statistics. Each module is supplied with appropriate documentation, in the form of Word files which can be edited to your own requirements, provided the source is acknowledged, and the copyright notice observed.

The software is freely available to educational institutions, and its use is encouraged. Other organisations can purchase the software for use.

The STEPS Consortium

The sites which comprised the STEPS Consortium were:

University of Glasgow	Department of Statistics (Lead Site)
University of Lancaster	Centre for Applied Statistics Department of Management Science
University of Leeds	Department of Statistics
The Nottingham Trent University	Department of Mathematics
University of Reading	Department of Applied Statistics
University of Sheffield	School of Mathematics and Statistics
UMIST	Department of Management Science

The problem-based approach & its advantages

What is a problem?

a problem has substantial discipline matter
a problem has a realistic scenario within the subject
a problem contains some elements where random variation is present
a problem should not be too complex for students to grasp
a problem is not necessarily solved when the statistical elements have been covered

Some advantages of the problem-based approach:

it can motivate interest via the student's own study area
it can reduce perceived conflict with lectures
it will allow integration with other laboratory material
it will allow a broad spectrum of problems to be addressed

Topics Covered

The topics covered by STEPS modules include:

Graphical Methods	Histograms, Stem & Leaf, Box Plots, Scatterplots, Time Plots
Variability	Short Term Unpredictability, Long Term Predictability
Sampling	Simple random samples, Stratification
Confidence Intervals	Confidence and Interval Estimation
Hypothesis Testing	Null & Alternative Hypotheses, Significance Level, Power, Randomising
Experimental Design	Blocking
Regression	Fitted Values, Residuals, ANOVA, Influential Points, Outliers
Discrete Data	Association, Goodness of Fit
Simple Statistical Models	Binomial, Poisson, Normal, Multinomial, Sampling Distributions

Evaluation

All the STEPS software was evaluated prior to public release, in a four-step process:

The first tier of evaluation took place at the design stage with anonymous evaluation by consortium members. This evaluation provided critical feedback on the viability of the proposed problem content from both a context and statistical point of view. It also provided the opportunity to comment on the educational aims and the technical structure proposed.
The second tier of evaluation took place once the problem design had been developed into a full specification and implemented by technical staff. This stage was also carried out anonymously by consortium members. This evaluation provided critical feedback on the mechanics of the problem, the success of the structure and the problem's ability to meet its educational aims.
The third tier of evaluation, by students, took place either in parallel with stage 2 or after comments from stage 2 evaluators had been received. This again provided critical feedback, this time from the intended users of the software. Students' comments were always considered very seriously.
The final tier of the evaluation process was by external evaluation. Selected teaching colleagues, from both the application and statistics departments, were asked to evaluate the material and to trial on their students. Their comments were invaluable, particularly in determining whether or not they would use the problem material in their teaching, what they found most useful about the material and whether or not they saw it achieving worthwhile educational aims.

Once these comments had been received, the authors used this information to make the final adjustments to their problem module(s).

Longer term review of the effectiveness of the software was carried out by nominated evaluators, using students in their own classes, once the software had been released to the academic community.

Other Relevant Web sites

: LTSN Maths, Stats & OR Network; The LTSN has taken on the role of disseminating information about the STEPS Project, now that funding for STEPS has ceased. MS&OR also maintains a searchable database of statistics software for teaching, which contains the abstracts of all the STEPS modules. Lastly, the Web site contains an article and a review of the STEPS software.
TLTP Central Web: The Web site of the Teaching and Learning Technology Programme
HEFCE: The Higher Education Funding Council for England
SHEFC: The Scottish Higher Education Funding Council
HEFCW: The Higher Education Funding Council for Wales
DENI: The Department of Education for Northern Ireland