Unpublished Manuscript

  • We cannot discuss assessment of students without also discussing student assignments. Why? The content of a course depends on the customized curriculum of each individual instructor, department, or even, in some cases, the institution. Therefore, here I am going to focus on what we might choose to assess, how we might choose to assess our students, and how we can design our assignments to assist us in our assessment strategies. Finally, I will present an example from my applided multiple regression course.

  • This project has two phases. In phase 1 various data sources are explored and the Directory of Academic Statisticians (DAS) is identified as the most reliable source of data on Statistics teaching staff. The number of staff in core Mathematical Science groups peaks in 1996 and has declined since then. The decline is related to RAE score. In Phase 2 a survey of university groups that identify with the discipline of Statistics is used to explore the past and present provision of Statistics teaching. The key groups for determining the future supply of Statisticians are those from within the Mathematical Sciences. These groups can be categorized as strong, marginal or weak, depending on their recent history and perceived prospects. This categorization is used to make projections of Staff numbers in 2010. A decline of between 7% and 22% is expected. The position in Medical Statistics is stable. Conclusions are drawn in the final section based on the survey returns and the analysis of the DAS data.

  • At the invitation of the CRAFTY subcommittee, a group a statisticians and mathematicians met October 12-15 for the purpose of addressing issues about the role of undergraduate mathematics in preparing students to study statistics and the role of statistics in the undergraduate mathematics curriculum. The group included representatives from industry as well as academia, and the academicians were from a wide variety of institutional types.

  • We base this report on a survey of liberal arts college departments of mathematical sciences. The purpose of the survey was to gain basic curricular and pedagogical information about the discipline of statistics within liberal arts colleges.

  • Hypothesis testing is one of the key concepts in statistics, yet it is also one of the least understood concepts. The purpose of this study was to investigate teachers' understandings of hypothesis testing, in an effort to generate insights in ways of supporting teachers' learning and enhancing teachers' capacity in designing effective strategies for teaching hypothesis testing. To this end, we conducted a professional development seminar and interviews with 8 high school statistics teachers in 2001 in Southeast US, in which we attempted to unpack the difficulties and conceptual obstacles teachers encountered as they tried to conduct or make sense of hypothesis testing. We found that teachers' difficulties in understanding and employing hypothesis testing were expressed in their non-stochastic conceptions of probability, their lack of understanding of the logic of indirect argument, and them not having conceived of hypothesis testing as a tool for making statistical inference. We conclude the article by offering promising pedagogical approaches for developing a deep and coherent understanding of hypothesis testing.

  • While there has been an impact on how statistics is being taught and increased satisfaction with the course, we still fall short of giving students the experiences they need to freely use statistical thinking and correct reasoning when they approach novel problems. While an introductory course cannot make novice students into expert statisticians, it should develop statistical thinking that can be applied to real world situations. Despite the proliferation of high quality new materials and technological tools, many instructors take a "black box" approach: simply using the materials and tools will somehow magically develop students' statistical thinking. What is needed is a method of teaching that is constantly linked to the goal of statistical thinking and provides teachers with the mechanism to evaluate how this goal is impacted by their teaching.

  • Statistical thinking focuses on properties that belong not to individual data values but to the entire aggregate. We analyse students' statements from 3 different sources to explore possible building blocks of the idea of data as aggregate and speculate on how young students go about putting these ideas together. We identify 4 general perspectives that students use in working with data, which in addition to an aggregate perspective include regarding data as pointers, as case values, and as classifiers. Some students seem inclined to view data from one of these 3 alternative perspectives, which then influences the types of questions they ask, the representations they generate or prefer, the interpretations they give to notions such as the average, and the conclusions they draw from the data.

  • In reflecting upon the possible components of a course of study for students doing doctoral work in the field called statistics education, it seemed that the preparation should contain most of the components of a model preparation program for doctoral students in mathematics education. In fact, except for the particulars of the discipline, I see very little difference in what I would recommend as the core of either doctoral program. There may be great benefit in having a major overlap in the coursework, seminar work, research practicum, and any work in the fields of education, psychology, and foreign languages in mathematics and statistics education programs. I would even advocate for a consideration of combined prgrams in Mathematics and Statistics Education at the doctoral level. In many universities in my country, from the practical point of view. Below I briefly discuss Core components of a statistics education doctoral program, and factors that are necessary for institutions to support quality doctoral work in statistics education.

  • A goal of this study is to verify, or modify, the genetic decomposition of the Central Limit Theorem through the identification of students who had developed a viable understanding of this theorem. Another goal of the present paper is to add to the body of knowledge concerning the development of statistical knowledge in college students by building on the work done by Mathews and Clark.

  • In the latest version of Tinkerplots (Konold & Miller, 2002), we introduce a new type of graphic display - the "hat plot." The inclusion of this representation will undoubtedly provoke many skeptical questions by teachers, statistics educators and curriculum developers: "What re these? Are they in the Standards? Are they used by statistician?" Given that they are neither in the Standards nor in the statisticians' tool box, the reasonable next question is "Why are they in Tinkerplots, and what are we supposed to do with them?" In briefly responding to these questions, I offer a rational for hat plots and suggest possible uses in the data analysis curricula.