Revision as of 17:03, 8 May 2016 edit 7804j (talk \| contribs) Extended confirmed users 3,650 edits Created stub based on the "Determining the number of clusters in a data set" page. Would require more details.		Revision as of 23:23, 29 May 2016 edit undo Dcirovic (talk \| contribs) Autopatrolled, Extended confirmed users, Pending changes reviewers, Rollbackers 253,275 edits m clean up using AWB Next edit →
Line 6: More precisely, if one plots the percentage of variance explained by the clusters against the number of clusters, the first clusters will add much information (explain a lot of variance), but at some point the marginal gain will drop, giving an angle in the graph. The number of clusters is chosen at this point, hence the "elbow criterion". This "elbow" cannot always be unambiguously identified.<ref>See, e.g., {{Cite journal \| ~~author~~ author1= David J. Ketchen, Jr & \|author2=Christopher L. Shook \| title = The application of cluster analysis in Strategic Management Research: An analysis and critique ~~\| title = The application of cluster analysis in Strategic Management Research: An analysis and critique~~ \| journal = [[Strategic Management Journal]] \| volume = 17 Line 48 ⟶ 47: <references/> {{comp-sci-stub}}▼ [[Category:Clustering criteria]] ▲{{comp-sci-stub}}

Elbow method (clustering): Difference between revisions