A1372
Title: Inference on union bounds
Authors: Xinyue Bei - The University of Texas at Austin (United States) [presenting]
Abstract: A union bound is a union of multiple bounds. Union bounds occur in a wide variety of empirical settings, such as difference-in-differences, regression discontinuity design, bunching, and misspecification analysis. A confidence interval is proposed for these kinds of bounds based on modified conditional inference. It is improved upon existing methods in a large set of data-generating processes. The new procedures give statistically significant results, unlike the pre-existing alternatives in the empirical applications.
