This paper explores a class of robust estimators of normal quantiles filling the gap between maximum likelihood estimators and empirical quantiles. Our estimators are linear combinations of M-estimators. Their asymptotic variances can be arbitrarily close to variances of the maximum likelihood estimators. Compared with empirical quantiles, the new estimators offer considerable reduction of variance at near normal probability distributions.
The original article can be found at http://dx.doi.org/10.1214/aos/1059655910. Article archived for private and non-commercial use with the permission of the author and according to publisher conditions. For further information see http://www.imstat.org/aos/.