Virtual Workshop on Missing Data Challenges in Computation, Statistics and Applications
The workshop was organized by Laura Balzano (IAS/University of Michigan), Bianca Dumitrascu (IAS/ SAMSI), and Boaz Nadler (IAS/Weizmann Institute of Science) and will take place virtually.
Missing data is ubiquitous in statistical analysis. In genomics, novel single cell technologies allow for the collection of data sets where individual cells are characterized by whether genes are expressed or not, but only the values exceeding a particular threshold can be detected. In social sciences, in survey data, participants might choose to not answer particular questions. In healthcare, only one dosage of a medication can be tried at any particular time, or discomfort associated with particular medications might compel a patient to drop out of a given treatment. While significant theoretical results in dealing with missing data exist, there is a wide variability in the set of tools used within particular disciplines. Domain specific knowledge and jargon make it difficult for experts from different disciplines to effectively communicate and share knowledge regarding challenges and state-of-the-art methodology. Bringing together practitioners and theorists alike, this workshop will provide a platform for discussing progress related to inference and computational challenges emerging across disciplines where missing data is an issue and identifying promising venues where theory provide insight into data analysis.
Speakers who have confirmed participation:
Gurinder Singh Atwal, Laura Balzano, Eric Chi, Mark Davenport, David Dunson, Barbara Englehardt, Anna Gilbert, Kosuke Imai, Rafael Irizarry, Julie Josse, Sanmi Koyejo, Rod Little, Grace Yi, Anru Zhang and Nancy Zhang.