Tackle the outliers

When we have a small data set, our estimation may be sensitive to the inclusion of one or several observations. An observation is an influential observation if dropping it from the analysis changes the key estimates by a practically "large" amount.

Solutions？
Trimmed mean:
 In the diving game evaluation, the highest and the lowest scores are eliminated. The five remaining scores are then added up and the total score is then multiplied by the difficulty factor for each dive and then by 0.6, which gives the final result. A tie is declared when two divers get the same total score. 

Median:
 another way to deal with outliers.