Theory

  • Traditional courses in statistics generally approach inference from a theoretical probability based perspective. Since the mathematical backgrounds of students is often not strong, many courses use computer based simulations to empirically justify ideas which are too complex or too abstract for most students. However, eventually, students must move from the empirical to the theoretical understanding of the concept if they are to apply these ideas to traditional inference methodologies. This paper questions the effectiveness of some of these strategies, and discusses how computer based technologies may be used effectively to bring together these theoretical and empirical perspectives.

  • We have an increasing number of students at Australian universities whose first language is not English. The English courses which many of these students take before being admitted are frequently inadequate for the study of technical subjects such as statistics which have a language of their own. Very little work has been done on the precise difficulties experienced by overseas students and how these difficulties could be alleviated. This paper discusses some of these problems which arise in first level university statistics courses and suggests some appropriate responses. In general these suggestions would probably benefit all students, not only those from overseas.

  • This paper addresses the importance of making both the women's and the men's worlds visible. Women and men should always be presented side by side in statistics. From that it is possible to judge if women and men are both visible to the same extent in the real world in all areas of society and to evaluate how far we have reached concerning the quantitative aspect of equal opportunity.

  • The paper considers the place of qualitative research in education, examining the significance of social context as a source of meaning for classroom processes. Ethnographic research methodology is considered as an approach to answering the question "What is happening when young children are working independently as part of a mathematics programme in a junior classroom?". There is strong potential for this methodology in classroom-based research.

  • This chapter deals with Exploratory Data Analysis (EDA) and is based on a detailed theoretical analysis of the latter.

  • Changes in educational assessment are currently being called for, both within the field of measurement and evaluation as well as in particular disciplines such as statistics. Tradional assessment of statistical knowledge typically look like textbook problems that either rely heavily on numerical calculations or on the ability to recall isolated pieces of information. Although this type of assessment seems to succed in providing instructors with a method for assigning numerical scores for determining letter grades ranking students within a course, these types of assessment rarly reveal information about how students actually understand and can reason with statistical ideas or apply their knowledge to solving statistical problems. As statistics instruction at the college level begins to change in response to calls for reform (e.g., Cobb, 1992) there is an even greater need for appropriate assessment methods and materials to measure students' understanding of probability and statistics and their ability achieve more relevant goals such as being able to explore data and to think critically using statistical reasoning. This paper attempts to summarize current trends in educational assessment and relate these to the assessment of student outcomes in a statistics course.

  • This chapter focuses on the intuitive scientist's ability to use base rate or distributional information in two of these inferential tasks: causal analysis and prediction. It will be argued that essentially the same characteristics of human inference are implicated in these tasks.

  • This paper discusses the background of the Hong Kong education system, the present status of statistics education in Hong Kong and the main weaknesses of the local statistics education. There are some suggestions for improvement offered.

  • A family of notorious teasers in probability is discussed. All ask for the probability that the objects of a certain pair both have some property when information exists that at least one of them does. These problems should be solved using conditional probabilities, but cause difficulties in characterizing the conditioning event appropriately. In particular, they highlight the importance of determining the way information is being obtained. A probability space for modeling verbal problems should allow for the representation of the given outcome and the statistical experiment which yielded it. The paper gives some psychological reasons for the tricky nature of these problems, and some practical tips for handling them.

  • In the present paper we first suggest a threefold classification of dependence relationships between pairs of events, then point out some misconceptions concerning these relationships, and, lastly, speculate as to the reasons that it is not customarily employed.

Pages

register