Hunting multiple outliers using Grubbs' test
Grubbs' test found that the maximum value could be an outlier, but what if there are more? Further outliers can be found by repeating Grubbs' test, after removing any previously identified outliers from the data.
To identify the point that was tested, the which.min()
or which.max()
functions can be used to find the index containing the largest or smallest value - remember we know which of these it is from the Grubbs' test output.
This exercise is part of the course
Introduction to Anomaly Detection in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Apply Grubbs' test to the nitrate data
grubbs.test(river$nitrate)
# Find row index of the max of the nitrate data
___(___)