Is the regression F-test doubly robust?
Abstract
We study the robustness of the F-test in random design linear models, and reach a somewhat nuanced conclusion. On the positive side, one of our main results is that the size of the test is close to its nominal level as soon as either the distribution of the normalised error vector is close to uniform on the unit sphere, or the design matrix, after applying a suitable column space-preserving orthogonalisation scheme, is close to being uniformly distributed. This provides a sense in which the F-test is doubly robust. Our conclusion is reached by establishing a Kolmogorov to Wasserstein distance Hölder continuity property controlling the departure of the F-statistic from its notional F-distribution under the null. Writing n, p and p0 for the sample size and the dimensions of the full and null models respectively, we prove that the Hölder exponent is 1/3 when min(p−p0,n−p) = 1 and 1/2 when min(p−p0,n−p) ≥ 2. On the other hand, these exponents are relatively small and cannot be improved in general, revealing that the size of the test may depart from its nominal level quite quickly as we move away from settings where the test is exact. In some cases, our conclusions may be improved by working with a local Kolmogorov distance that focuses on discrepancies between distribution functions in the right tail.
Related
- Doubly robust target inference for generalized linear regression with completely missing covariates
- Win-Ratio Regression for Prioritized Composite Outcomes in Observational Studies: Doubly Robust and Efficient Estimation with Future-Score Correction
- A Doubly Robust Approach to Evaluating the Impact of Hospital Length of Stay on Post‐Fracture Recovery in Older Adults With Cognitive Impairment
- Doubly Robust Deep Kernel Tests for Structured Outcomes
- Doubly-robust causal inference for multi-valued treatment regimes with recurrent neural networks
BibTeX
@misc{xia2026regression,
title = {{Is the regression $F$-test doubly robust?}},
author = {Lucy Xia and Oliver Y. Feng and Yang Feng and Min Xu and Richard J. Samworth},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.39905},
eprint = {2609.39905},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.39905},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Is the regression F-test doubly robust?
AU - Lucy Xia
AU - Oliver Y. Feng
AU - Yang Feng
AU - Min Xu
AU - Richard J. Samworth
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.39905
UR - https://arxiv.org/abs/2609.39905
AB - We study the robustness of the F-test in random design linear models, and reach a somewhat nuanced conclusion. On the positive side, one of our main results is that the size of the test is close to its nominal level as soon as either the distribution of the normalised error vector is close to uniform on the unit sphere, or the design matrix, after applying a suitable column space-preserving orthogonalisation scheme, is close to being uniformly distributed. This provides a sense in which the F-test is doubly robust. Our conclusion is reached by establishing a Kolmogorov to Wasserstein distance Hölder continuity property controlling the departure of the F-statistic from its notional F-distribution under the null. Writing n, p and p_0 for the sample size and the dimensions of the full and null models respectively, we prove that the Hölder exponent is 1/3 when min(p−p_0,n−p) = 1 and 1/2 when min(p−p_0,n−p) ≥ 2. On the other hand, these exponents are relatively small and cannot be improved in general, revealing that the size of the test may depart from its nominal level quite quickly as we move away from settings where the test is exact. In some cases, our conclusions may be improved by working with a local Kolmogorov distance that focuses on discrepancies between distribution functions in the right tail.
ER -