On a distribution-free quantile estimator. (Q5958633)

A distribution free non-kernel quantile estimator \(HD_{p}\) of the \(p\)\,th population quantile was introduced by \textit{F. E. Harrell} and \textit{C.E. Davis} [Biometrika 69, 635--640 (1982; Zbl 0493.62038)]. In this paper, we use a level crossing empirical distribution function to propose a new estimator \(HD_{p(lc)}\) which is a weighted version of \(HD_{p}.\) The exact efficiency and simulation efficiency of \(HD_{p(lc)}\) relative to the \(HD_{p}\) quantile estimator are studied. From both the theoretical and computational points of view, the new estimator is more efficient in many cases, especially for the tails of the distributions and small sample sizes.