用层三角变换作混合模型中的参数估计

ESTIMATION OF PARAMETERS IN MIXED MODELS USING LAYER TRIANGULAR TRANSFORMATION

在混合线性模型中估计方差分量,最广泛应用的方法是极大似然(ML)法和约束极大似然(REML)法,从数理统计理论的高度来看,这些方法相当完美,但从数值计算的角度来看,却比较繁琐.

A new alternative for estimating parameters in some widely used mixed linear models is proposed. The approach is called as the layer transformation estimation. Using the same preliminary transformation for both testing and estimation gives us an integrated set of procedures for the full analysis of mixed linear models. The proposed procedures are computationally stable and space saving.