Proceedings

  • When designing a new basic course in statistics for students in Environmental Engineering at Lund<br>University, our aim was that assessment should be an integral part of the course. We found that there<br>were several factors to be considered, such as how the assessment should be in line with the goals of<br>the course and with the teaching method. One piece of the assessment is a major project and we<br>discuss how we have organized it to give timely and constructive feedback to the students. In this<br>course, the students have their own personal computer available at each lesson and at the exam. This<br>opens up for new possibilities when assessing student learning but also create new problems. A<br>number of pros and cons of using computers at the exam are given.

  • In the paper, we argue that the persistence of students' difficulties in reasoning about the stochastic despite significant reform efforts in statistics education might be the result of the continuing impact of the formalist mathematical tradition. We first provide an overview of the literature on the formalist view of mathematics and its impact on statistics instruction and learning. We then re-consider some well-known empirical findings on students' understandingof statistics, and form some hypotheses regarding the link between student difficulties and mathematical formalism. Finally, we briefly discuss possible research directions for a moreformal study of the effects of the formalist tradition on statistics education.

  • Comments on statistical articles in the popular press by first-year economics students studying statistics in Australia and South=East Asia are analyzed. Three common weakness are described - lack of appreciation of journalistic style, disregarding statistical variation, and incorrect percentage statements. Differences between the groups are described and implications for teaching such courses are discussed.

  • In this experiment, we investigate the correspondence between how graph-readers visually inspect a graph to answer a comparison question about two groups and the justifications they offer. We recorded how people visually inspected graphs using a device that restricted how much data they could see at any given time. Students offered a variety of justifications for why two groups differed (e.g., slices, cut-points, modal clumps), and these appear to correspond to how they visually parsed the data.

  • I am inclined to believe that despite the different settings in which statisticians work, it is nevertheless important for them to be aware of good teaching and learning techniques, so that they may continue in their own lifelong learning, dealing with the continual increase of new information to be learned, and also so that they may teach others, whether in an academic stetting with students or in another type of setting in government or industry. To this end, I think that course work and experience in teaching should be required of all graduate students in statistics, as well as for students in other disciplines.<br><br>However, I have some concerns about teacher training programs that focus exclusively on lesson plans, syllabi, handouts, and lectures. In deeping with the suffestions for good teaching I have described, I would like to see teacher training programs help graduate students learn about the teaching and learning process, learn now to develop adn facilitate cooperative learning actrivities, become experienced with the role of assessment (and alternative forms of assessment), and learn about current ways of improce teaching in their discipline (that is, the use of software as a teaching tool, the use of pojects, and so on). The development of programs such as these could lead to a new generation of improved statistics teachers and statisticians who are able to work more effectively in any type of setting. I look forward to seeing this happen.

  • This experiment contrasts learning by solving problems with learning by studying examples, while attempting to control for the elaborations that accompany each solution step. Subjects were given different instructional materials for a set of probability problems. They were either provided with or asked to generate solutions, and they were either provided with or asked to create their own explanations for the solutions. Subjects were then tested on a set of related problems. Subjects in all four conditions exhibited good performance on the near transfer test problems. On the far transfer problems, however, subjects in two cells exhibited stronger performance: those solving and elaborating on their own and those receiving both solutions and elaborations from the experimenter. There also was an indication of a generation effect in the far transfer case, benefiting subjects who generated their own solutions. In addition, subjects' self-explanations on a particular concept were predictive of good performance on the corresponding subtask of the test problems.

  • Drawing from web-based materials previously developed to supplement on-campus offerings of an introductory statistics course for graduate students in education, the author made an initial offering of an on-line virtual class in the fall of 2001. Poor student performance and dissatisfaction with this initial course organization led to a deeper reading of the literature on online teaching in general and the online teaching of statistics in particular. A much greater degree of instructor supplied organization, direction and interaction were incorporated into other offerings of the course during the fall and spring of 2003. Final examination scores and course evaluations improved markedly over the first online offering but remained somewhat lower and more variable than the results from on-campus offerings of the same course. Suggestions for improvements are offered based on instructor observations and student feedback.

  • This paper reports some difficulties and strategies the students have in solving conditional probability problems with computer simulation. The difficulties are related to programming in the software used and with the trend of the relative frequencies graphic representation when the number of cases increases. The main strategy for estimation was taking the last value of the relative frequencies as the requested probability.

  • Our comparative studies investigate the influence of different representations (i.e. formulas or graphical models and numeric formats) on the understanding of "big ideas" in stochastics (e.g. characteristics of probability, conditional probability, distribution, significance). We know from previous work (e.g. Sedlmeier &amp; Gigerenzer, 2001) that special tree-representations combined with frequency-formats increase the performance in understanding dramatically. Another aspect of the experiments is the utility of different presenting-modes (e.g. static vs. dynamic, imitation vs. learning by doing). The pupils of age 15-19 receive a computer-based training with different representations resp. modes on basic probability tasks. The effects of the training are measured by subsequent tests. Thus we obtain insight, if they succeed easily in using the learned representations and if they benefit from it. The first results support the assumption that groups of pupils trained with frequency-representations have a better understanding of key-problems in stochastics.

  • "IT" or "Internet Technology" is a rising star in distance education. With the rapid development of new technologies, educators around the world have more tools and greater out-reaching power than ever before. What are IT education and its associated technology? How can statistics education benefit from it? How do you teach a statistics course on-line and what are the unique advantages and disadvantages of teaching statistics through the net? This paper summarizes my experiences designing and teaching an elementary statistics web course and gives my answers to some of the previous questions. I will in this paper present the way the course was taught and how specifically some of the course content was delivered using the "WebCT"(WebCT) software. Additionally some pedagogical recommendations will be made.

Pages