Proceedings

  • Simulating quickly a large number of repetitions of an experiment is a powerful tool in statistics. Simulations can be performed and explored individually by students in the classroom with graphics calculators like the TI83(Plus). Applications are estimating the probability of an event, predicting the profit in a game of chance, approximating the probability distribution of a random variable, drawing samples from a population, testing the quality of the random number generator. These applications will be illustrated with examples.

  • Statistical reasoning is often presented as a variety of problems that are explained through a series of "tests" - usually leaving many students bewildered. One of the key elements that is missing from such treatment is building a foundation for understanding what statistical reasoning is and how it works. Simulations, made possible by technology such as graphing calculators, can provide students a conceptual basis for inference. Generating sampling distributions can help them analyze the behavior of a given statistic, explore whether a given observation is unlikely, investigate how changing sample size changes the distribution, explore different kinds of distributions and what makes them different, and give them a sense of how to reason from data. Examples from the world outside of the classroom illustrate how simulation can be a tool in making sensible decisions and give students opportunities to see why statistics is important.

  • Drawing from web-based materials previously developed to supplement on-campus sections of an introductory statistics course for graduate students in education, the author started offering an on-line virtual class in the fall of 2001. The course, designed for doctoral students already participating in a program making extensive use of web-based materials, relied on students working independently with the on-line material (that included course lectures and notes) supported by access to the instructor using e-mail and the telephone. End of course performance was lower and much more variable than had been expected. Many students expressed the need for much more organization and contact with the instructor. Comparisons are made with reports of more successful virtual courses suggesting the need for a much greater degree of instructor supplied organization and direction.

  • Teaching probabilities to preschoolers is a very important task as daily decision making is based on probabilities. Although all children are well acquainted with probabilistic terms very few discussions are held in their classrooms because most of the preschool teachers are not prepared to teach probabilities. This study presents a way of teaching probabilities using Internet games and the constructivism theory.

  • This paper will report about the realisation and use of St@tNet, an interactive internet course on introductory statistics. St@tNet has been realised by a consortium of several French-speaking universities for distance education purposes. After a survey of the resources provided by Internet for teaching statistics, and especially of similar courses, we will present the product and its current use.

  • Emerging evidence suggests that people do not have difficulty judging covariation per se but rather have difficulty decoding standard displays such as scatterplots. Using the data analysis software Tinkerplots, I demonstrate various alternative representations that students appear to be able to use quite effectively to make judgments about covariation. More generally, I argue that data analysis instruction in K-12 should be structured according to how statistical reasoning develops in young students and should, for the time begin, not target specific graphical representations as objectives of instruction.

  • This paper describes a project that involves statistical researchers and software designers in a collaboration designed to accelerate progress in research on statistical thinking and the development of effective software tools for statistical education; the two tools in question are TinkerPlots and Fathom. Most of the paper is devoted to a description of teachers analyzing a dataset first without, then with technology and to a discussion of the implications of such observations for both research and software development.

  • This paper contrasts two types of educational tools: a route-type series of so-called statistical minitools (Cobb et al., 1997) and a landscape-type construction tool, named Tinkerplots (Konold & Miller, 2001). The design of the minitools is based on a hypothetical learning trajectory (Simon, 1995). Tinkerplots is being designed in collaboration with five mathematics curricula and is open to different approaches. Citing experiences from classroom-based research with students aged ten to thirteen, I show how characteristics of the two types of tools influence the instructional decisions that software designers, curriculum authors, and teachers have to make.

  • In an ideal world, science students would act as scientists do: investigating their own questions, designing experiments, and so forth. This paper reports on curriculum development and field testing that takes a step in this open-ended direction. To do this, we have focused on integrating more data analysis into science activities; this also gives students a chance to use more mathematics, in an understandable context. This mathematics includes work with functions and variation. A closer look at plausible activities shows us that principles of measurement connect these elements; furthermore, a broad view of measurement reconnects us to our original goal: to expose students more directly to the nature of science.

  • Research on learning and commercial software development competes strongly for a project's scarce resources, and yet they have widely overlapping goals. If they could be made to coexist, their synergy could improve both processes. On the research side, to use software to help understand how students perceive and learn statistical concepts requires a software platform that is stable, easy for students to use, and flexible enough to allow different models to be tried; that is, the research benefits from a smoothly functioning development process. On the development side, there is great need for insight into the learning process to inform the software design, and need for research methods to test whether any given design works with students and improves their statistical understanding.

Pages