JRSSB Mar 28, 2026

Double cross-fit doubly robust estimators: Beyond series regression

Authors
Larry Wasserman Sivaraman Balakrishnan Alec McClean Edward H Kennedy
Research Topics
Machine Learning
Paper Information
  • Journal:
    Journal of the Royal Statistical Society Series B
  • DOI:
    10.1093/jrsssb/qkag057
  • Published:
    March 28, 2026
  • Added to Tracker:
    Mar 28, 2026
Abstract

Abstract Double cross-fit doubly robust (DCDR) estimators, which train nuisance function estimators on separate samples, are effective new estimators for causal functionals. We establish several novel theoretical results for them, building on recent work. We provide a structure-agnostic error analysis, which holds with generic nuisance functions and estimators. Then, we propose n-consistent DCDR estimators with undersmoothed local polynomial regression and k-Nearest Neighbours and a minimax rate-optimal DCDR estimator with undersmoothed kernel regression. Finally, we demonstrate inference is possible even in the non-root-n regime with a central limit theorem for an undersmoothed DCDR estimator. We reinforce our theoretical results with simulation experiments.

Author Details
Larry Wasserman
Author
Sivaraman Balakrishnan
Author
Alec McClean
Author
Edward H Kennedy
Author
Research Topics & Keywords
Machine Learning
Research Area
Citation Information
APA Format
Larry Wasserman , Sivaraman Balakrishnan , Alec McClean & Edward H Kennedy (2026) . Double cross-fit doubly robust estimators: Beyond series regression. Journal of the Royal Statistical Society Series B , 10.1093/jrsssb/qkag057.
BibTeX Format
@article{paper1092,
  title = { Double cross-fit doubly robust estimators: Beyond series regression },
  author = { Larry Wasserman and Sivaraman Balakrishnan and Alec McClean and Edward H Kennedy },
  journal = { Journal of the Royal Statistical Society Series B },
  year = { 2026 },
  doi = { 10.1093/jrsssb/qkag057 },
  url = { https://doi.org/10.1093/jrsssb/qkag057 }
}