Growth Curve Model With Linear Admissible And Minimax Estimators

Consider growth curve model as follows:Different estimators of regression coefficients matrix B have been discussed in many documents, especially the least square estimate, and there have been rather mature theories about the admissibility of general growth curve model parameter estimation. These researches were spread in the homogeneous admissible estimators and the inhomogeneous admissible estimators, under matrix loss and quadric loss.We discussed the two following aspects mainly:First, we recalled the preliminary of liner models theory and discussed the Mini max estimator problems in statistical decision theory under the homogeneous admissible estimators L₀ and the inhomogeneous admissible estimators L₁. We have found the admissible Mini max estimators of linear estimable function KBL under the quadric loss, and proved the estimator is unique.Second, we researched the linear admissible estimators and linear admissible Mini max estimators of linear estimable function KBL in growth curve model with common mean parameter under matrix loss.