Meaningful Individual Differences in Statistics Cognition

This chapter focuses on the understanding and use of individual differences in statistics cognition. We argue that individual differences can be classified along a continuum ranging from within an individual (internally derived) to an outside source (externally prescribed), and that where an individual differences falls on the continuum may have important implications for how individual differences are used to describe, control for, predict, or explain findings in scholarly research. We argue that individual differences are more useful when they meaningfully pertain to cognitive development, and outline how motivation (using goal orientation and self-determination theory) can be used as an individual difference. We conclude with a discussion of aligning motivational goals and how online courses could adapt themselves to student motivational profiles.

Affect in Statistics Cognition

This chapter focuses on affective process in statistics education which could influence cognitive development. We begin with a discussion of short-term high-intense affective features (emotions) and use the most well researched construct in computer and statistics education (anxiety) to illustrate how these processes can influence learning. We then discuss long term low intense affective features (moods) and outline how moods can contribute to statistical attitudes. We argue that affective features must be continuously assessed throughout the entire learning process, and discuss theorize how online learning environments can use the principles of differentiation to enhance affect toward statistics education.

Developing Statistics Cognitions

This chapter focuses on the development of statistics cognition, framing the discussion on the need to enhance cognitive development. We argue that by understanding how cognitive processes have been shown to inhibit learning, we can differentiate between types of errors in statistics education. By understanding the operationalized difference of a bias and misconception, those interested in statistics education can identify the sources of these errors, and subsequently develop a means to attenuate their effect. Using dual process theory, we argue that classifying the source of errors and differentiating between biases and misconceptions educators can use errors to enhance the development of statistics literacy, reasoning, and thinking.

Understanding Statistics Cognition

This chapter focuses on understanding the use of and relationship among the features of statistics cognition: literacy, reasoning, and thinking. We argue that research on statistics cognition is fragmented, which is problematic for understanding how these constructs can be unified to support education. We then review methods of quantifying cognitions, involving studies which have attempted to categorize and parse cognitive processes. This information is then used to synthesize a new approach to understanding statistics cognition, proposing a model which makes specific predictions about the relationship of these features. The model and definitions of cognitions presented in this chapter are used as a basis of discussion cognition throughout the remainder of the book.

The Purpose of Statistics Education

This chapter briefly introduces the field of statistics education, and provides a short synopsis for each of the seven proceeding chapters. In introducing the field, the importance of integrating technology into all aspects of the curriculum, and using a well-designed data driven methodology which takes an interdisciplinary approach, is argued to be central to the success of developing an online statistics course. By integrating technology and using the scientific method to align course materials and adhere to fundamental educational psychological findings, we argue that the primary objective of statistics education—to enhance statistics cognition—can be achieved.

Concluding Remarks

In this chapter, we provide brief concluding remarks which focus on summarizing key frameworks discussed throughout the first six chapters. We argue that by developing a testable model of statistics cognition we can make specific predictions about learning and errors which can help provide educators with the guidance needed to curb the influence errors can have on learning. Additionally, by developing a cognitive curriculum, which is designed to assess student affect and make use of meaningful individual differences, we can enhance the quality of statistics education in online environments. We conclude this chapter by outlining several future directions that can help facilitate our understanding of statistics cognition.

A Cognitive Curriculum

This chapter provides a discussion of developing a curriculum for a modern statistics course which aims to improve statistics cognition. We begin by examining micro-level curricular considerations, such as designing learning objectives and assessments which can allow transfer of cognitive processes. Then, we discuss the implications of macro-level curricular considerations, such as tracking, and the need to search for a mismatch between the learner and their environment. Collectively, we argue that such practices allow educators to develop a cognitive curriculum. We conclude the chapter with a discussion of how online learning environments inherently lend themselves to a cognitive curriculum and provide numerous benefits for the educator and learner.