摘要
当平差模型中存在复共线关系时，未知参数的最小二乘估计很不可靠。提出了在无偏估计类中解决这一问题的有效方法—附加条件法，并从理论上证明了这一方法。
The least Square estimates are not reliable when there exists multicollinearity in adjustment model. To solve the problem statisticians improve least square estimates by biased estimates in biased estimation class. This paper presents an efficient method-Addition Restricted Condition Method (ARCM)-to solve the problem in unbiased estimation class,and proves that the method can improve least square estimates.
出处
《武汉测绘科技大学学报》
CSCD
1995年第1期46-50,共5页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金
关键词
复共线关系
均方误差
附条件法
最小二乘
multicollinearity
mean squared error
restricted condition
ridge estimate
