By Kyle Barriger, Castilleja School
Introductory statistics at the secondary level has traditionally been taught with a focus on surveys, experiments, and inferential methods to support analysis of those studies. In most cases, this work has involved small samples that could be analyzed on a calculator. Most problems in the popular textbooks are still structured this way.
With the growth of big data and the increased use of machine learning to process increasing volumes of data, the content of the course needs to shift. Students need understand how to analyze datasets that contain thousands of observations across a hundred or more variables. They also need to be able to go beyond bivariate analysis and consider multiple explanatory variables. This poster will explore the changes that have been made in the AP Statistics curriculum at Castilleja School over the last decade to address these concerns. The goal of this poster is to stimulate conversation around the appropriate mix of introductory statistical content for secondary students in today's world.