English

l_p-norm based James-Stein estimation with minimaxity and sparsity

Statistics Theory 2015-05-29 v2 Statistics Theory

Abstract

A new class of minimax Stein-type shrinkage estimators of a multivariate normal mean is studied where the shrinkage factor is based on an l_p norm. The proposed estimators allow some but not all coordinates to be estimated by 0 thereby allow sparsity as well as minimaxity.

Keywords

Cite

@article{arxiv.1402.0302,
  title  = {l_p-norm based James-Stein estimation with minimaxity and sparsity},
  author = {Yuzo Maruyama},
  journal= {arXiv preprint arXiv:1402.0302},
  year   = {2015}
}

Comments

11 pages, A new section for unknown scale case is added and a minor revision is done

R2 v1 2026-06-22T02:59:40.145Z