User blog comment:Flonnaru/Results of Non-Drum Expeditions sparkle effect/@comment-24430017-20150609005754/@comment-25283969-20150609182527

first of all everything is possible,you can get 10 times in row normal success even if the GS rate is 80%,its all random as everything spread around the sample mean,its simply mean they too many/less GS than expected,it only screws up the confidence interval to minimize the impact,we look for outliner with the 'Grubb-Test' google it read it and understand whats the point of eliminating outliers