The American Statistical Association (ASA) DataFest is a nationally coordinated data analysis competition where teams of up to five students have a weekend to attack a large, complex and surprise dataset. Biostats students composed two teams: ‘GoBiostat’ (Xingyan Wang, Lanqui Yao, Yiling Liu and Qi Gao) and ‘Exactly Normal’ (Emily Almeida, Leigh Nicholl, Madison Berry, Jeremy Weber and Rituparna Basu). This year’s data set was has not been publically released but previous years’ data sets have included crime data from the LAPD, dating data from eHarmony, and energy use data from GridPoint. Competitors are given the data set and must come up with their own research question and conduct the appropriate analysis to answer that question. "I think it was a good competition for self-teaching, as well as teamwork. We could discover anything we wanted from the dataset. It was also good practice for using software," said Xingyan Wang, Masters Student.
The purpose of DataFest is to expose students to challenging questions with immediate practical significance that can be addressed through data analysis. Masters Student Rituparna Basu said of her experience, "DataFest gave me an appreciation for the differences between data science and biostatistics. It was a fun challenge to work on a dataset that was extremely large and unrelated to medicine." The weekend is structured around the data lifecycle, with lectures and hands-on sessions focused on data concepts, project planning and data science workflows, processing and analysis, and finally data dissemination.
ASA Datafest was held at Duke University from Friday, March 31 to Sunday April 2nd, and co-hosted by the UNC Department of Statistics and Operations Research and also the NC State Statistics Department. Students from Duke, UNC, NC State University attended.
DataFest was founded at UCLA in 2011 and has been held annually at Duke since 2011.
