132
v1v2 (latest)

Bi-ss^*-concave distributions

Abstract

We introduce a new shape-constrained class of distribution functions on R, the bi-ss^*-concave class. 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 s-concave density f has a bi-ss^*-concave distribution function FF and that every bi-ss^*-concave distribution function satisfies γ(F)1/(1+s)\gamma (F) \le 1/(1+s) where finiteness of γ(F)supxF(x)(1F(x))f(x)f2(x), \gamma (F) \equiv \sup_{x} F(x) (1-F(x)) \frac{| f' (x)|}{f^2 (x)}, the Cs\"org\H{o} - R\év\ész constant of F, plays an important role in the theory of quantile processes on RR.

View on arXiv
Comments on this paper