Figure 1
From: Robust clustering in high dimensional data using statistical depths
Illustration of spatial depth function. y1 is located deep inside the cloud of x's, summing up e will result in a vector with the norm close to , since unit vectors have different directions and they cancel each other out. The depth of y1 is approaching 1. y2 is outside the data cloud, the sum of e has a large norm, thus the depth is approaching 0.