I am a fourth-year Ph.D. candidate in Economics at the University of Wisconsin-Madison, working in econometrics and statistics. I am advised by Jack R. Porter, Bruce E. Hansen, and Harold D. Chiang. My research develops statistical theory for inference with modern nonparametric and machine learning estimators, with generalized U-statistics as a unifying framework.
I am especially interested in jackknife methods, generalized and infinite-order U-statistics, random forests, and local inference for causal parameters such as heterogeneous treatment effects.
Working papers
-
Jackknife Variance Estimation for Hájek-Dominated Generalized U-Statistics
I study ratio-consistency of the jackknife variance estimator for generalized U-statistics whose variance is asymptotically dominated by their Hájek projection, with applications to distributional nearest-neighbor regression.
-
Orthogonal Inference for Conditional Z-Estimation without Cross-Fitting: A Distributional Nearest-Neighbor Approach
I develop pointwise inference for localized conditional estimating equations using distributional nearest-neighbor weights, orthogonal scores, same-sample machine-learned nuisance estimates, and jackknife variance estimation.
Manuscript available upon request · Research page
Selected work in progress
- Distribution-on-distribution regression with optimal transport.
- Asymptotic theory for random forests, joint with Harold D. Chiang and Christian Döbler.
This GitHub profile provides an overview of my current research and teaching and archives selected code, computational materials, and earlier project repositories. The most current overview of papers, projects, and teaching materials is available on my website.
I have taught and assisted courses in econometrics and mathematical economics at the University of Wisconsin-Madison, including:
- ECON 703, Mathematical Economics I / Ph.D. Math Camp.
- ECON 410, Introductory Econometrics.
Teaching materials and evaluations are linked from my teaching page.