Regression Adjustment for Ratios of Treatment Effects in Randomized Experiments
Abstract
We study regression adjustment for ratios of treatment effects in completely randomized experiments. The existing literature adjusts the numerator and denominator separately, but this approach misses the efficiency target, loss of which matters more when richer or high-dimensional covariate information and flexible or regularized prediction methods are used to pursue further efficiency gains. We propose a two-step estimator that directly predicts the relevant transformed outcome. Using cross-fitting, our method accommodates high-dimensional first-stage prediction while keeping the final adjustment fixed-dimensional, thereby avoiding instability from a growing number of adjustment covariates. We further develop persistence-based LASSO theory that does not require sparsity, permits more covariates than observations, and allows cross-validated penalty selection under prediction-level conditions. For additional efficiency gains, our augmented two-step estimator nests the benchmark adjustment spaces and is therefore asymptotically no less efficient than the benchmark estimators, while its feasible conservative variance estimator satisfies the same efficiency ordering. Simulation studies and a real-data analysis demonstrate that our proposed estimator performs better than existing methods.
Related
- Regression adjustment in completely randomized experiments with many covariates
- Covariate Adjustment in Randomized Experiments: A Unified Framework for Decision and Practice
- Higher Order Asymptotics of Regression Adjustment Estimators for Causal Inference
- Automated, Efficient, and Model-Free Inference for Randomized Clinical Trials via Data-Driven Covariate Adjustment
- Exact Risk Ratios for Weighted Data Selection in Linear Regression
BibTeX
@misc{kakehi2026regression,
title = {{Regression Adjustment for Ratios of Treatment Effects in Randomized Experiments}},
author = {Haruo Kakehi},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35666},
eprint = {2610.35666},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35666},
}
RIS
TY - UNPB
TI - Regression Adjustment for Ratios of Treatment Effects in Randomized Experiments
AU - Haruo Kakehi
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35666
UR - https://arxiv.org/abs/2610.35666
AB - We study regression adjustment for ratios of treatment effects in completely randomized experiments. The existing literature adjusts the numerator and denominator separately, but this approach misses the efficiency target, loss of which matters more when richer or high-dimensional covariate information and flexible or regularized prediction methods are used to pursue further efficiency gains. We propose a two-step estimator that directly predicts the relevant transformed outcome. Using cross-fitting, our method accommodates high-dimensional first-stage prediction while keeping the final adjustment fixed-dimensional, thereby avoiding instability from a growing number of adjustment covariates. We further develop persistence-based LASSO theory that does not require sparsity, permits more covariates than observations, and allows cross-validated penalty selection under prediction-level conditions. For additional efficiency gains, our augmented two-step estimator nests the benchmark adjustment spaces and is therefore asymptotically no less efficient than the benchmark estimators, while its feasible conservative variance estimator satisfies the same efficiency ordering. Simulation studies and a real-data analysis demonstrate that our proposed estimator performs better than existing methods.
ER -