Online Program Home
  My Program

Abstract Details

Activity Number: 120 - SPEED: Variable Selection and Networks
Type: Contributed
Date/Time: Monday, July 31, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Learning and Data Science
Abstract #324868 View Presentation
Title: Fostering Undergraduate Data Science
Author(s): Mark Ward* and Fulya Gokalp Yavuz
Companies: Purdue University and Purdue University and Yildiz Technical University
Keywords: data science ; undergraduate training ; mentoring ; statistical projects
Abstract:

Innovative training methods are essential for data science. We advocate an approach to data science training for undergraduate students that utilizes several types of computational tools, including R, bash, SQL, and XPath, often used in tandem. We also advocate introducing students to research opportunities early in their undergraduate experiences. We believe that data science training should be an interdisciplinary experience for such students. Students benefit from blending their research and coursework, as well as having support from peers and faculty research mentors. Active learning environments and living-learning communities both lend themselves well to unifying such data science training opportunities. We share lessons learned from two NSF training grants for undergraduates. We give some insights for researchers, professors, and practitioners, about how to effectively embed real-life examples into data science learning environments. We advocate building on a foundation of team-oriented, data-driven projects, courses, seminars, problem solving sessions, and opportunities for students to develop their own projects and communicate the results.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association