Identification of extreme values in reduced samples

Asked

Viewed 19 times

0

I am running an analysis where I need to find a reference value for small groups of observations (between 3 and 10). As some samples present at least a very discrepant value I will try to identify outlier. I found some references to modified z-score and also modified IQR however, the formulas differ and I have doubts about which formula should be implemented. Anyone have any idea? Is there a package / function that is more suitable for identifying extreme values in small-sized samples?

No answers

Browser other questions tagged

You are not signed in. Login or sign up in order to post.