Median Regularity and Honest Inference
Statistics Theory
2022-06-08 v1 Methodology
Statistics Theory
Abstract
We introduce a new notion of regularity of an estimator called median regularity. We prove that uniformly valid (honest) inference for a functional is possible if and only if there exists a median regular estimator of that functional. To our knowledge, such a notion of regularity that is necessary for uniformly valid inference is unavailable in the literature.
Keywords
Cite
@article{arxiv.2206.02954,
title = {Median Regularity and Honest Inference},
author = {Arun Kumar Kuchibhotla and Sivaraman Balakrishnan and Larry Wasserman},
journal= {arXiv preprint arXiv:2206.02954},
year = {2022}
}
Comments
10 pages