Analyzing Real Data Demands Database Skills

• Activity Number: 342
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Education
• Author(s): Robert Carver*+
• Companies: Stonehill College
• Keywords: GAISE ; Statistical educaiton ; database ; Real data

Abstract

Among the key recommendations of the GAISE Report are use of technology to de-emphasize calculation and the use of real data in introductory courses. Since GAISE was issued, we have witnessed the data deluge accompanied by rapidly increasing availability of data from public sources, as well as exciting activity in the public and private sectors to plumb granular data from disparate sources in the pursuit of improved healthcare, enhanced security, and business opportunity. As statistics educators continue to redefine the scope and content of the introductory course, it is important for students to learn methods for obtaining, cleaning, organizing and manipulating large datasets from multiple sources prior to analysis. This paper presents the case that we must "make space" for basic database skills (relational tables, joining on common keys, etc.) as well as devoting more attention to the challenges of preparing real-world dirty data. Using current statistical software, the paper illustrates exercises through which these skills can be introduced and incorporated into the course in ways that are accessible and well-motivated.