|
Abstract:
|
In this talk, we discuss causal thinking, its importance to an undergraduate education, and ideas/opportunities for developing it in introductory statistics courses for general audiences. We define causal thinking as the habitual mental process of assessing the complex relationships that often exist between several variables. In our world of ubiquitous data and statistically-based arguments, it is essential. Effective causal thinkers are everywhere, and can apply causal inference concepts such as association, causality, and confounding to their understanding of the world, even if they lack the mathematical background to grasp their formal definitions. Developing causal thinking in students teaches them how to think, perhaps the most important goal of an undergraduate education, and shows how experience, judgement, and critical thinking are important to statistics and data science. Teaching causal thinking in introductory statistics does not require huge changes to existing courses, and can be as simple as asking the right research questions, modeling your thought processes, giving students experience explaining theirs, and employing causal diagrams.
|
