Selection of Quasi accurate Observations and “Hive off” Phenomena about the Estimators of Real Errors

Being different from the previous methods, used to detect gross errors in observations,such as statistical test and robust estimate, a new method named as “Quasi Accurate Detection of gross errors”(QUAD) has been proposed in ref. .The key of QUAD is how to select the Quasi accurate Observations(QAO) reasonably. An effective scheme, which is divided into two steps, is summarized. In the first step called “Preliminary Selection”, the observations are classified into 4 sorts among which only the “2 sort” and the parts of “3 sort” are able to be chosen as QAOs. In the second step, called “Fine Selection”, the observations corresponding to rather less |Δ^|, which are calculated at the previous step, are chosen as QAOs. The distribution characters of the estimators of real errors would present distinct and interesting “hive off” phenomena which are illustrated in this paper with the figures and tables on the basis of the result of the example discussed by many scholars. The abnormal values would be rather larger than those of the normal ones in the tables, or would float on the top of the figures, and the rest would precipitate in the lower part of the figures. Based on this character of the estimators of real errors, the multiple outliers are able to be identified and detected distinctly.