Planning observational studies with unobserved confounding in mind

Thu, Aug 10, 8:30 AM

Samuel PimentelChair

ENAR

4 Presentations

Increasing Power for Observational Studies of Aberrant Response: An Adaptive Approach

8:35 AM - 8:55 AM

Siyu Heng (New York University)

Co-authors: Hyunseung Kang (University of Wisconsin-Madison), Dylan Small (University of Pennsylvania), Colin Fogarty (Massachusetts Institute of Technology)

Model Selection for Reducing Sensitivity to Unobserved Confounding in Controlled Pre-Post Designs

8:55 AM - 9:15 AM

Thomas Leavitt (Harvard University)

Design Sensitivity and Its Implications for Weighted Observational Studies

9:15 AM - 9:35 AM

Daniel Soriano (UC Berkeley)

Co-authors: Samuel Pimentel (University of California-Berkeley), Melody Huang (University of California, Berkeley)

Robust Machine Learning for Treatment Effects in Multilevel Observational Studies Under Cluster-level Unmeasured Confounding

9:35 AM - 9:55 AM

Hyunseung Kang (University of Wisconsin-Madison)

Discussant

Michael Baiocchi