Robust Maximum Likelihood Estimation of Huber in Geodetic Networks and Multi-outlier Detection

Least squares adjustment suffers by the outliers. In order to employ the least squares methods, it is necessary to be ensured that all of the observations are correctly measured. Before employing the least squares methods the pre-adjustment data screening should be performed, until the gross errors among the abservations are detected. A fter doing least squares adjustment the post-adjustment data screening have to be employed to detect the small outliers observation according to Baarda is theory. This process is valid for just one erroneous observation, it means that if there are several erroneous observations among the set of observations, one cannot correctly detect the outliers. In such cases the robust methods of estimation must be employed because it is insensitive to the outliers and gross errors.

Robust Maximum Likelihood Estimation of Huber in Geodetic Networks and Multi-outlier Detection Keywords:

Adjustment , M-estimation of Huber , Outliers , Reweighting , Robust estimation