Precursors to the Data Explosion: Teaching How to Compute with Data

• Activity Number: 210
• Type: Invited
• Date/Time: Monday, August 5, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Education
• Author(s): Nicholas J. Horton*+ and Benjamin S. Baumer and Daniel Theodore Kaplan and Randall Pruim
• Companies: Smith College and Smith College and Macalester College and Calvin College
• Keywords: Data Science ; Big Data ; Statistical Computing ; Introductory Statistics ; R ; Reproducible Analysis

Abstract

Computational data analysis is an essential part of modern statistics, but our introductory statistics courses and much of our undergraduate statistics curriculum often neglect this fact. In this talk, I will discuss ways to provide a practical foundation for students to learn to "compute with data" as defined by Nolan and Temple Lang (TAS, 2010). This includes initial exposure in introductory statistics classes to some of the realities of non-textbook data, as well as the structure of an undergraduate "data science" class where students participate in the entire data analysis cycle (from forming a statistical question, data acquisition, cleaning, transforming, modeling and interpretation). By introducing students to tools for data management, storage, manipulation, visualization and reproducible analysis that are common in data science and applying those tools to real scenarios, we are preparing them to think statistically in ways that will allow them to address the impending data explosion.