Confidence Sets Based on Sparse Estimators Are Necessarily Large
Statistics Theory
2010-01-09 v2 Methodology
Statistics Theory
Abstract
Confidence sets based on sparse estimators are shown to be large compared to more standard confidence sets, demonstrating that sparsity of an estimator comes at a substantial price in terms of the quality of the estimator. The results are set in a general parametric or semiparametric framework.
Keywords
Cite
@article{arxiv.0711.1036,
title = {Confidence Sets Based on Sparse Estimators Are Necessarily Large},
author = {Benedikt M. Pötscher},
journal= {arXiv preprint arXiv:0711.1036},
year = {2010}
}
Comments
Revision containing correction of some minor errors and typos; some additional remarks added