This comment offers three descriptions of "p[subscript rep]" that start with a frequentist account of confidence intervals, draw on R. A. Fisher's fiducial argument, and do not make Bayesian assumptions. Links are described among "p[subscript rep]," "p" values, and the probability a confidence interval will capture…

A picture of a 95% confidence interval (CI) implicitly contains pictures of CIs of all other levels of confidence, and information about the "p"-value for testing a null hypothesis. This article discusses pictures, taken from interactive software, that suggest several ways to think about the level of confidence of a CI,…

Our research in statistical cognition uses both qualitative and quantitative methods. A mixed method approach makes our research more comprehensive, and provides us with new directions, unexpected insights, and alternative explanations for previously established concepts. In this paper, we review four statistical cognition studies that used mixed…

Compelling arguments for reform of statistical practices have been made in many disciplines, in some cases over several decades, but achieving reform has proved difficult. We discuss how reform has progressed--or not progressed--in psychology, medicine, and ecology and describe case studies of attempts by pioneering journal editors to change…

Practitioners and teachers should be able to justify their chosen techniques by taking into account research results: This is evidence-based practice (EBP). We argue that, specifically, statistical practice and statistics education should be guided by evidence, and we propose statistical cognition (SC) as an integration of theory, research, and…

In the first issue of "Australian Educational Computing," in 1986, Cumming and Abbott reported a controlled comparison of top-down and bottom-up teaching strategies for Grade 5 and 6 students' use of a simple logic programming language. They found that both strategies were rated highly by students and teachers, and gave useful learning;…

Confidence intervals (CIs) give information about replication, but many researchers have misconceptions about this information. One problem is that the percentage of future replication means captured by a particular CI varies markedly, depending on where in relation to the population mean that CI falls. The authors investigated the distribution of…

Wider use in psychology of confidence intervals (CIs), especially as error bars in figures, is a desirable development. However, psychologists seldom use CIs and may not understand them well. The authors discuss the interpretation of figures with error bars and analyze the relationship between CIs and statistical significance testing. They propose…

Common attitudes in 1985 concerning the use of computers in Australia's universities are looked at humorously from the perspective of 1995. (MSE)

In an introductory psychology statistics course that required students to work in small groups, it was found that letting students select their own groups worked well. There were no differences in success between the groups that could be classified as mixed-ability and those that were homogeneous. (RM)

A study comparing the performances and preferences of college statistics students in streamed and mixed-ability groups revealed that both types of class organization are workable, but students prefer varied abilities in small work groups. (AM)

This paper is an introductory discussion of industrial training, artificial intelligence (AI), and AI applications in training, prepared in the context of the United Kingdom Training Commission (TC) program. Following an outline of the activities and aims of the program, individual sections describe perspectives on: (1) training needs, including…

This report summarizes and interprets the discussions at a seminar on artificial intelligence (AI) training domains and knowledge representations which was sponsored by the United Kingdom Training Commission. The following broad areas are addressed: (1) the context, process, and diversity of requirements of training and training needs; (2)…

Gives a brief outline of the development of Artificial Intelligence in Education (AIED) which includes psychology, education, cognitive science, computer science, and artificial intelligence. Highlights include learning environments; learner modeling; a situated approach to learning; and current examples of AIED research. (LRW)

Educational design encompasses many aspects of educational software development but needs to be extended to Project Design (PD) by inclusion of a strategy for dissemination. This crucial aspect of PD should be considered from the start and usually involves commercialization. Models for commercialization are diverse, and the choice can have…