English

Bi-$s^*$-Concave Distributions

Statistics Theory 2020-10-12 v2 Statistics Theory

Abstract

We introduce new shape-constrained classes of distribution functions on R, the bi-ss^*-concave classes. In parallel to results of D\"umbgen, Kolesnyk, and Wilke (2017) for what they called the class of bi-log-concave distribution functions, we show that every ss-concave density ff has a bi-ss^*-concave distribution function FF for ss/(s+1)s^*\leq s/(s+1). Confidence bands building on existing nonparametric bands, but accounting for the shape constraint of bi-ss^*-concavity, are also considered. The new bands extend those developed by D\"umbgen et al. (2017) for the constraint of bi-log-concavity. We also make connections between bi-ss^*-concavity and finiteness of the Cs\"org\H{o} - R\'ev\'esz constant of FF which plays an important role in the theory of quantile processes.

Keywords

Cite

@article{arxiv.2006.03989,
  title  = {Bi-$s^*$-Concave Distributions},
  author = {Nilanjana Laha and Zhen Miao and Jon A. Wellner},
  journal= {arXiv preprint arXiv:2006.03989},
  year   = {2020}
}

Comments

68 pages, 24 figures; replaces and extends arXiv:2006.03989 by Laha, Miao, and Wellner

R2 v1 2026-06-23T16:07:03.901Z