The Linear Mixed Models Family Derived from GGM Model

摘要：

Unified theory of least squares was given by Rao (1971, 1972, 1973) and Rao and Mitra (1971). In the paper we extend the generalized inverse (ginverse) matrix (R + XGX)- involved in unified theory of least squares to g-inverse (R + ZGZ)-, where Z is the coefficient matrix of random effects of the linear mixed models. We define the linear mixed models family derived from general Gauss-Markoff model, and apply unified theory of least squares to this linear mixed models family. The related results with Mols’s (2003) and Wang’s (2010) are obtained in the paper.

关键词： general Gauss-Markoff model unified theory of least square linear mixed model best linear unbiased estimate best linear unbiased nredictor

作者: Ying Ma Shiqing Wang

作者单位: College of Mathematies and Information Sciences, North China University of Water Conservancy Electric Power, Zhengzhou, 450011, China

会议类型: 国际会议

会议名称: 2010 International Conference on Application of Mathematics and Physics(2010国际数理科学与气象学术研讨会暨2010空间天气学研讨会 AMP2010)

会议地点: 南京

会议语种:英文

页码: 577-580

在线出版日期: 2010-05-08（万方平台首次上网日期，不代表论文的发表时间）