A CROSS-VALIDATORY CHOICE OF SMOOTHING PARAMETER IN ADAPTIVE LOCATIONESTIMATION

This article proposes a new data-driven method for selecting the smoot hing parameter involved in constructing kernel-based adaptive location estimators. The method consists of minimizing a cross-validatory crit erion with respect to the bandwidth occurring in the kernel-type estim ators of the efficient score function. It is shown that the location e stimator with a data-driven bandwidth selector is indeed an adaptive e stimator. A simulation study reveals that the method is also practicab le, showing that our estimator performs well in comparison with some o ther well-known location estimators. It also shows that our method has comparable finite sample performance with the bootstrap method of sel ecting the smoothing parameter and yet has great computational advanta ges.