Editor’s Letter—Vol. 33, No. 4
Dear CHANCE Colleagues,
In 2006, Netflix hosted a data competition aimed at improving their movie recommendation system. The winners were awarded $1 million in 2009 for a model that offered more than 10% improvement over the company’s own recommendation model. Netflix planned to host a follow-up competition, but reversed the decision in 2010 after a class-action lawsuit (Doe v. Netflix) was filed against them, alleging privacy law violations concerning the data set publicized for the original competition.
Two years earlier, in 2008, researchers at the University of Texas at Austin, Arvind Narayanan and Vitaly Shmatikov, showed that it was possible to identify specific customers in the Netflix data set (suggesting that even political and religious affiliations could be determined), even though Netflix had performed a form of cursory anonymization.
The Netflix example illustrates the importance of preserving confidentiality when sharing data sets. In this special issue of CHANCE, we focus on statistical data privacy and confidentiality. I wish to thank the three guest editors: Saki Kinney, senior research statistician at RTI International; Fang Liu, professor and director of graduate studies in applied and computational mathematics and statistics at the University of Notre Dame, senior editorial board member for BMC Medical Research Methodology, and co-editor of CHANCE‘s “O Privacy, Where Art Thou?” column; and Aleksandra Slavković, professor of statistics, with appointments in the departments of Statistics and Public Health Sciences and the Institute for Computational and Data Sciences at Penn State University, as well as associate editor of the Annals of Applied Statistics and Journal of Privacy and Confidentiality, and co-editor of CHANCE‘s “O Privacy, Where Art Thou?” column.
In columns, we turn to teaching and sports. In the “Teaching Statistics in the Health Sciences” column, Erin Blankenship and Ella Burnham share their online teaching experiences, a topic that many teachers can relate to during the COVID-19 pandemic. In the “Taking a Chance in the Classroom” column, Evangeline Reynolds explains how to create engaging assignments using flipbooks, demonstrating the method using the R flipbookr package. Finally, in “Beyond the Box Score,” Christopher Bilder discusses the flagstick dilemma in golf: whether to leave the flag in or out of the hole.
Amanda Peterson-Plunkett