An Improvement of the James-Stein Estimator with Some Shrinkage Points using the Stein Variance Estimator

초록

Consider a p-variate(p ≥ 3) normal distribution with mean and covariance matrix Σ = 2I p for any unknown scalar 2. In this paper we improve the James-Stein estimator of in cases of shrinking toward some vectors using the Stein variance estimator. It is also shown that this domination does not hold for the positive part versions of these estimators.

키워드