On Some Classes of Estimators Derived from the Positive Part of James–Stein Estimator

This work consists of developing shrinkage estimation strategies for the multivariate normal mean when covariance matrix is diagonal and known. The domination positive part James–Stein estimator (PPJSE) over (JSE) relative to balanced loss function (BLF) analytically proved. We introduce a new class estimators which ameliorate PPJSE, then we construct series polynomial improve PPJSE; also, any this can be ameliorated by adding it term higher degree. end paper simulation studies confirm performance suggested estimators.