Research

  • The way in which businesses compete is rapidly changing. Businesses must constantly strive to offer "better" products and services than their competitors. South African Companies on the whole need to improve the quality of their products in order to be a player in the global market. Managers must decide how to overcome the many problems that prevent quality products and services. One of the aims of this study was to establish whether managers in the manufacturing industry of KwaZulu Natal are aware of the uses of statistics in decision making. In this study, it was found that most of the quality managers either do not use statistical process control techniques or use them seldom or very seldom. It was established that the majority of the respondents do not use statistical process control charts. The above facts indicate the need for the awareness of the uses of statistical process control techniques and charts to improve the quality of products. Results of the "Survey on Statistical Quality Control Techniques" used by Managers in the Manufacturing Industry of KwaZuluNatal, are also given (Hargreaves, 1999).

  • This paper follows two previous studies regarding an analysis of the efficacy and efficiency of the academic system. A bivariate, multilevel model has been proposed in order to measure the relative efficacy of each course by quantifying its contribution in obtaining a particular outcome, net of individual, environmental and course- specific factors. The concept of technical efficiency is also presented and two evaluating methodologies, which are based on a frontier function, are analysed. Both methods take into account differences in students' academic ability (which characterize the university system) and these are analysed on a geographical basis, thereby aiming at an investigation of differentials throughout all the regions in Italy. The results of this analysis will be presented during the conference.

  • This paper reports on the use of a system designed to encourage statistics students to read the course text as a primary source of information and ideas. Reading and limited assessment would precede classroom teaching. The system has been implemented for eight semesters. Summaries of data collected will be presented, as will qualitative feedback from students.

  • Many schools, like Carnegie Mellon University, are now teaching introductory statistical reasoning courses in a way that emphasizes conceptual understanding of the basic ideas of data analysis. There are several challenges in teaching such a course; foremost among them is the difficulty of conveying a sense of the "Big Picture." This paper describes a computerized learning tool that we have developed to help overcome this obstacle. This tool is a cognitive tutor in which students solve data-analysis problems and receive individually tailored feedback. We discuss our cognitive tutor's use in the course and its measured effectiveness in a controlled experiment.

  • Previous research has shown a consistent, albeit weak, negative correlation (r ( -0.20) between statistics anxiety and statistics achievement. Additionally, self-efficacy has been shown to be a consistent predictor of both anxiety and achievement. This study showed that if self-efficacy is assumed to reflect a distribution of confidence, then the relationship between statistics anxiety and statistics achievement can be explained by the differential impact of two features of the self-efficacy distribution. Although only outcome expectancies predict statistics achievement, statistics anxiety is predicted by the interaction between outcome expectancies and outcome uncertainty. It is suggested that these results are indicative of at least two sources (or cognitive interpretations) of statistics anxiety, namely lack of confidence about one's ability and uncertainty in one's performance. The results are discussed in terms of cognitive appraisals of threat and challenge.

  • Preservice Mathematics teachers are faced with the task of learning Mathematics subject content and developing pedagogical knowledge. This paper describes an attempt to address these tasks simultaneously by designing a course in which preservice teachers collect data related to learners' understanding of statistics and fractions, and develop their own statistical understanding and expertise through analysis of this data. The preservice teachers' statistical thinking was assessed by analysis of articles they wrote based on their own data. It is asserted that even in the presence of the requisite raw materials, statistical thinking is not intuitive and requires explicit teaching.

  • The importance of statistical graphics, as well as their practical use in day-to-day scientific research, makes it worth assessing and appraising teachers' conceptions concerning this matter. Accordingly, we should shed some light on the most specific components of dealing with such graphics as understood by math secondary level teachers. At the end, we try to give some guidelines that could be useful when elaborating on a content for teachers' training.

  • The findings reported in this article came from a study which took place in an introductory college-level statistics course and which adopted a nontraditional approach to statistics instruction that had variation as its central tenet. The conjecture driving the study was that poor understanding of statistical concepts might be the result of instructional neglect of variation and that instruction which puts emphasis on building student intuitions about variation and its relevance to statistics should also lead to improved comprehension of other statistical concepts. The results of the study point to a number of critical junctures and obstacles to the conceptual evolution of variation. The article discusses one of those critical junctures and obstacles, the understanding of histograms.

  • This paper reports on research that created a controlled environment for interviewing individual students on the topic of sampling, allowing for cognitive conflict from other students. At various points in the interview the student was shown video extracts with contrasting views to those expressed and ask for a reaction. Outcomes are discussed with respect to (a) the outcomes for 37 students, in terms of their reaction to the cognitive conflict presented, and (b) the methodology, in terms of modeling cognitive aspects of a classroom environment in a controlled setting.

  • Our paper describes a suite of studies involving students' statistical thinking in Grades 1 through 8. In our key studies (Jones et al., 2000, Mooney, in press), we validated Frameworks that characterised students' thinking on four processes: describing, organizing, representing, and analyzing and interpreting data. These studies showed that the students' thinking was consistent with the four cognitive levels postulated in a general developmental model. We also report on two teaching experiments, with primary students (Jones et al., 2001; Wares et al., 2000) that used the Framework to inform instruction. Teaching experiment results showed that children produced fewer idiosyncratic descriptions of data, possessed intuitive knowledge of center and spread and were constrained in analysis and interpretation by knowledge of data context.

Pages