Share This

“Most important in cluster analysis, a distance measure is used to determine how far one point is from another, or from the center of a proposed cluster. For numerical attributes, distance can be a common Euclidean measure, (x-y)2. For multiple attributes, the individual squared differences are summed—giving equal weight to each measure. If attributes have highly different scales, the data might be scaled first. Distance between categorical data is often arbitrary, but is sometimes reduced to zero or one.”

« Back to Glossary Index Download Tooltip Pro
By |February 1st, 2019|Comments Off on distance