Approaches to broadening the statistics curricula

Abstract

Recently, there has been a lot of discussion about what a statistics curriculum should contain, and which elements are important for different types of students. For the most part, attention has been understandably focused on the introductory statistics course. This course services thousands of students who take only one statistics course. In the United States, the course typically fulfills a general education requirement of the university or a degree program. There has also been considerable activity regarding the use of computers to present statistical concepts and to leverage the Web and course management software to interact with students. Recently, there has been debate as to whether statisticians should make ambitious changes using resampling, the bootstrap, and simulation in place of the more traditional mathematical topics that are seen as the fundamentals or origins of the field (Cobb, 2007). It is unclear that we are achieving the goals of basic statistical literacy by focusing on formulae or even by concentrating almost exclusively on methodology. Instead, we believe the field and students would be significantly better served by showing the challenges and applicability of statistics to everyday life, policy, and scientific decision making in many contexts, and by teaching students how to think statistically and creatively. In contrast to the activity at the introductory level, there has been much less attention paid to updating the statistics curricula for other categories of students. While smaller in number, these students-undergraduate majors and minors, masters, and doctoral students-are very important, as they are the ones who will use statistics to further the field and improve the quality of research. Other disciplines (e.g., biology, geo graphy, and political and social sciences) are increasingly appreciating the importance of statistics and including statistical material in their curricula. Further, statistics has become a broader subject and field. However, the statistics curricula at these levelshave not changed much past the introductory courses. Students taking courses for just 2 years may not see any modern statistical methods, leading them to a view that the important statistical ideas have all been developed. More importantly, few students will see how these methods are really used, and even fewer will know at the end of their studies what a statistician actually does. This is because statisticians very rarely attempt to teach this; instead, they labor over the details of various methodologies. The statistics curricula are based on presenting an intellectual infrastructure in order to understand the statistical method. This has significant consequences for improved quantitative literacy. As the practice of science and statistics research continues to change, its perspective and attitudes must also change so as to realize the field's potential and maximize the important influence that statistical thinking has on scientific endeavors. To a large extent, this means learning from the past and challenging the status quo. Instead of teaching the same concepts with varying degrees of mathematical rigor, statisticians need to address what is missing from the curricula. In our work, we look at what statistics students might do and howstatistics programs could change to allow graduates to attain their potential. © 2009 Springer Netherlands.