April 13, 2015 •Kelley MacEwen
This weekend, undergraduates from universities in the Washington D.C. metro area took part in the first ever ASA DataFest hosted in the nation's capital. The event was hosted at Summit's office in coordination with the University of Maryland's Joint Program in Survey Methodology (JPSM), and also sponsored by the generous folks at the American Institutes for Research, Mathematica, Washington Statistical Society, and the DC chapter of the American Association for Public Opinion Research (AAPOR).
The festivities began on Friday, April 10th, with a reception that allowed participants, sponsors, and industry professionals to network and get to know each other. As a data-driven competition using real-world data, DataFest is not only fun, but also provides students with insight into how professionals use these skills in their careers. Employers also take notice of the event, and may identify DataFest participants as potential candidates for internships or job opportunities.
Around 7 pm, Summit Principal Albert Lee and JPSM Professor Frauke Kreuter wished the students luck and handed it over to the data sponsors, who then revealed the datasets that the students would be analyzing over the weekend. The students were also reminded that the data must be kept secret so other DataFest participants can be equally surprised and challenged.
Photo by Sean O'Brien, Stanton Communications
Once the dataset was revealed, the students hurried to their chosen conference rooms and began brainstorming what to do with the data. Throughout the weekend, VIP Consultants from sponsor organizations were available to help the students talk through their approaches, troubleshoot coding problems, and dry-run presentations.
DCDataFest hosted seven teams from nearly as many schools: American University, University of the District of Columbia (UDC), Howard University, Georgetown University, University of Maryland, and University of Maryland, Baltimore County (UMBC). The students were also diverse in their studies, representing majors such as international political economy, computer science, economics, applied statistics, history, physics, mathematics, psychology, journalism, American studies, and Asian studies.
Frauke and Amy help team ReJin on Day 2 of DataFest.
Throughout the weekend, a number of experts presented "Tech Talks" for the students to learn more about concepts relevant to their analysis. Tech Talks included:
- Evgeny Klochikhin, AIR: "Text mining and machine learning: examples from life."
- Joshua Tokle, AIR: "Using data visualization techniques to communicate results."
- Josh Logan, Census: "Telling stories with data to communicate to clients."
- Ed Dieterle, Summit: "Presentation skills."
Fueled by delicious food and lots of caffeine, the teams worked diligently throughout the weekend in preparation for the presentations on Sunday afternoon. During the presentations, the judges (from Mathematica, the Pew Charitable Trusts, and the data sponsor company) assessed each team on three categories: insight, data visualization, and use of outside data. Each team did an excellent job with their analysis and presentations, with top prizes going to:
- Best Insight: ReJin (pictured, right)
- Best Use of Outside Data: Terps
- Best Data Visualization: DataFusion
Thank you to everyone who made the inaugural DCDataFest a huge success: the sponsors, the volunteers, and especially the students! We can't wait to see what's in store for next year.
