华侨大学学报（自然科学版）2011，Vol.32Issue(5)：584-587,4.
复共线性下的主成分全最小二乘估计
Total Least Square Estimator of Principal Components under Multicollinearity
摘要
Abstract
The total least square estimator of principal components is proposed to avoid inversing the singular matrix under explanatory variables of multi-dimensions with multicollinearity. Under certain conditions, we prove by numerous test that it has smaller mean square errors (MSE) than least square estimator (LSE).关键词
最小二乘估计/全最小二乘估计/主成分/复共线性Key words
least square estimator/ total least square estimator/ principal components/ multicollinearity分类
数学引用本文复制引用
刘文丽,吕书龙,梁飞豹..复共线性下的主成分全最小二乘估计[J].华侨大学学报（自然科学版）,2011,32(5):584-587,4.基金项目
国家自然科学基金资助项目(11001054) （11001054）
福建省教育厅科研基金资助项目(JB08026,JB08027) （JB08026,JB08027）
