Detection and Adjustment of Gross Errors In Survey Data

Baarda's traditional gross error test method was used to test and eliminate the gross errors in the data. The data with gross errors were processed by robust estimation method and traditional adjustment method respectively, and the results were compared with those before adding gross errors. The advantages and disadvantages of different gross error processing methods were compared. It is concluded that under the condition of ensuring a certain number of iterative calculations, robust estimation can achieve the purpose of resisting gross errors. Compared with robust estimation, Baarda gross error detection can ensure the calculation efficiency on the premise of meeting certain accuracy requirements when there is only one gross error in the data. When the data contains multiple gross errors, the robust estimation method can be used for processing.