BEHAVIOUR OF JACKKNIFE ESTIMATORS IN TERMS OF ASYMPTOTIC DEFICIENCY UNDER TRUE AND ASSUMED MODELS

摘要

The problem on jackknifing estimators is investigated in the presence of nuisanceparameters from the viewpoint of higher order asymptotics. It is shown that theasymptotic deficiency of the jackknife estimator relative to the bias-adjusted maximumlikelihood estimator (MLE) is equal to zero under true and assumed m.odcls. Moreover,the asymptotic deficiency of the MLE or the jackknife estimator under the assumedmodel relative to that under the true model is given.