In this work an analysis of some task variables of statistical problems which can be proposed to the students to be solved on the computer, are presented. The objective of this didactical-mathematical analysis is to provide criteria of selection of the said problems, directed to guiding the students' learning towards the adequate meanings of the statistical notions and to the development of their ability to solve problems.
This paper discusses a curriculum, called Reasoning Under Uncertainty (RUU), which emphasizes reasoning and learning-by-doing as methods for helping students understand the hows and whys of statistics.
Some of you may not be familiar with the Quantitative Literacy Project (QLP) with which I have been involved, and this is expected. There are several copies of the 62 pages QLP Sampler available for you to look at. This publication provides some idea about the instructional material we have developed. It might be helpful to give you an overview of the QLP first, and then have a discussion and interchange of ideas.
This publication provides a historical background to the development of statistics and probability and an analysis of current research into the pedagogical issues associated with this area of mathematics. The final section contains information about resources of all types.
It is sometimes said that learning probability at an introductory level is not difficult since many probability questions are just questions about proportion. However, students often perform badly on probability questions and one reason for this might be an inadequate familiarity with proportions. In order to investigate this we developed a self-completion test instrument of 10 questions needing an understanding of proportion. Our students took about 25 minutes to complete this test. The questions were arranged with the simpler questions at the start, and the harder questions towards the end. The most difficult question, included partly as a way of finding out which students really did understand probability, asked students to find the chance that a pile of four bricks would reach five high before a pile of three bricks if new bricks were added at random to the two piles, shown as an outline diagram. This question, a version of one discussed by Monks (1985) is best tackled with a tree diagram. All questions, except one, were open-ended.
This paper will describe one approach to using visualization in learning statistics. The approach uses the ability of computers to perform statistical experiments (with the parameters determined by the learner) and display the results dynamically (as they occur). We will refer to the method as dynamic visual experimentation. We will use the term random phenomena to refer to the broad class of situations whose mathematical analysis requires statistical or probabilistic concepts or methods.
This article describes our positive and negative experiences with the RS program and with the Simon and Bruce views on teaching.
Rather than elaborate Simon's argument here, I briefly describe two software tools we've developed, highlighting aspects that emphasize the relation between probability and data analysis. I also report some results from our primary test site, a high school in Holyoke, Massachusetts.
A method that enables people to obtain the benefits of statistics and probability theory without the shortcomings of conventional methods because it is free of mathematical formulas and is easy to understand and use is described. A resampling technique called the "bootstrap" is discussed in terms of application and development. (KR)
The statistics course given as part of Psychology I in 1976 is described.