validation_measures: Validation Measures

In ilangurudev/approxmapR: ApproxMAP (APPROXimate Multiple Alignment Pattern)

Validation Measures

Usage

  Cluster validation measures supported in find_optimal_k()

Arguments

Average Distance Between Clusters	The average distance between clusters (FPC Documentation)
Average Distance Within Clusters	The average distance within clusters (reweighted so that every observation, rather than every distance, has the same weight) (FPC Documentation)
Average Distance Within Clusters / Average Distance Between Clusters	Average Distance Within Clusters /Average Distance Between (FPC Documentation)
Within Cluster Sum of Squares	A generalization of the within clusters sum of squares (k-means objective function), which is obtained if d is a Euclidean distance matrix. For general distance measures, this is half the sum of the within cluster squared dissimilarities by the cluster size (FPC Documentation)
Dunn Index	Is equal to the Minimum Separation / Maximum Diameter. Where the minimum separation is the minimum distance of a point in the cluster to a point of another cluster and the maximum diameter is the maximum within cluster distance (FPC Documentation). High values on the Dunn Index indicate the presence of compact a well-separated clusters.
Silhouette Index	“The silhouette width of a point measures the proximity of the point to its own cluster relative to the proximity to other clusters” (Halkidi, Batistaki, & Vazirgiannis, 2001). The silhouette index is the average silhouette width of clusters and ranges from -1 to 1. A value closer to -1 indicates that the point is on average closer to another cluster than the one to which it belongs, while a value closer to 1 indicates the point's average distance to its own cluster is smaller than any other cluster. A higher silhouette index value indicates the presence of compact and separated clusters.

References

1. Dalton, L., Ballarin, V., & Brun, M. (2009). Clustering algorithms: on learning, validation, performance, and applications to genomics. Current genomics, 10(6), 430–445. https://doi.org/10.2174/138920209789177601

2. Halkidi, M., Batistakis, Y., and Vazirgiannis, M. (2001). On clustering validation techniques. Journal of Intelligent Information Systems. 17(2:3), 107 – 145.

3. Rousseeuw, P. (1987), Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53-65.

4. https://www.rdocumentation.org/packages/fpc/versions/2.2-9/topics/cluster.stats

ilangurudev/approxmapR documentation built on March 22, 2022, 1:15 p.m.