基于验后方差估计原理探测与剔除粗差

摘要

将抗差估计的思想融入到粗差探测的算法中,设计出对模型误差特别是粗差具有抵抗能力的粗差探测算法.应用最小二乘法来计算观测值的参数、残差、协因数阵及单位权的初值,再根据残差和有关的参数,按所选择的权函数,计算每个观测值的权,经过迭代计算求得观测值的残差,按照统计检验的方法剔除粗差.通过实验证明,基于验后方差估计原理导出的选权迭代具有很强的粗差探测能力.%The idea of robust estimation is brought into the algorithm of detecting gross errors, in order to design the model errors,especially with the algorithm of resist errors. First, we calculate the parameters of the observed values, residual errors, co-factor matrix and the initial value of unit weight. Based on residual errors and parameters, we calculate the new weight value for each observation according to the weight function. Through iterative calculation, we may obtain residual errors of the observation, then we use the statistical methods to eliminate gross errors. The experiment proves that it has the good ability of detection of gross errors.