ESTIMATION OF VARIANCES IN ANIMAL-MODEL AND REDUCED ANIMAL-MODEL FOR SINGLE TRAITS AND SINGLE RECORDS
ESTIMATION OF VARIANCES IN ANIMAL-MODEL AND REDUCED ANIMAL-MODEL FOR SINGLE TRAITS AND SINGLE RECORDS
复制标题
DOI：
10.3168/jds.s0022-0302(86)80546-x
复制
发表时间：
1986-05-01
影响因子：
3.5
通讯作者：
HENDERSON, CR
中科院分区：
文献类型：
--
作者：
HENDERSON, CR
简化的动物模型可以用于最好的线性无偏预测，这导致与动物模型相比，需要求解的方程数量大大减少。同样，简化的动物模型可用于最小方差二次无偏估计和约束最大似然估计的方差估计。对于动物模型和简化动物模型下的方差估计，这些方法都需要混合模型方程的系数矩阵的广义逆。因此，使用简化的动物模型可以显著降低这种矩阵的阶数。给出了这些估计方法在动物模型和简化动物模型下的简单实例。
A reduced animal model can be used for best linear unbiased prediction, and this results in a large reduction in number of equations to be solved compared with the animal model. Similarly, the reduced animal model can be used for estimation of variances by minimum variance quadratic unbiased estimation and by restricted maximum likelihood. Generalized inverses of coefficient matrices of mixed model equations are required for these methods of estimation of variances under both the animal and the reduced animal model. Consequently, use of the reduced animal model can markedly reduce the order of such matrices. Simple examples are presented for these methods of estimation under both the animal model and the reduced animal model.