About Me
Econometrics and Statistics · University of Wisconsin-Madison
I’m a fourth-year Ph.D. student in Econometrics at the University of Wisconsin-Madison, advised by Jack Porter and Harold D. Chiang.
I develop statistical theory for inference with modern nonparametric and machine learning estimators, with generalized U-statistics as the unifying framework. One strand of my research builds local inference procedures for causal parameters, such as heterogeneous treatment effects. In this work, I show that the standard remedy of sample splitting can be avoided without sacrificing validity. Avoiding sample splitting preserves the scarce local information that makes these problems hard in the first place.
A second strand provides the theoretical foundations for this approach. It establishes when the jackknife, a simple, assumption-light, and widely used method, remains valid for the complex, high-order estimators these procedures rely on. This extends classical theory to settings it did not previously cover.
Contact
For research, teaching, or seminar inquiries, email me at: