抗差估计在测量粗差处理中的应用

Application of Robust Estimation in MeasurementGross Error Processing

在测量数据处理时,经典的最小二乘估计方法对数据的粗差敏感度非常高,抗差效果较差。针对这个问题,学界提出了抗差估计的概念。本文对一种广义极大似然估计方法进行了简单介绍,通过一个算例对最小二乘和抗差估计两种方法所得结果进行了比较。结果证明,比较数据在存在粗差时,以广义极大似然估计为代表的抗差技术具有较明显的优势。

In the measurement data processing,the classical least square estimation method is very sensitive to the gross error of the data,and the anti error effect is poor.To solve this problem,the concept of robust estimation is proposed.In this paper,a generalized maximum likelihood estimation method is introduced,and the results of the two methods are compared by an example.The comparison data proves that the robust technique represented by generalized maximum likelihood estimation has obvious advantages when there is gross error.