Quiz on Ward Clustering and Lance-Williamson Formula

What is the primary goal of Ward's clustering?

• Minimize the number of clusters.

• Minimize the sum of squared distances between points within clusters.

• Maximize the distance between clusters.

• Maximize the sum of squared distances between points within clusters.

Which formula is used to define the distance between two clusters in Ward's clustering?

• Manhattan distance formula.

• Lance-Williamson formula.

• Euclidean distance formula.

• Cosine similarity formula.

In Ward's clustering, the distance between two clusters is calculated based on the:

• Increase in variance caused by merging the two clusters.

• Maximum distance between points in the two clusters.

• Minimum distance between points in the two clusters.

• Average distance between points in the two clusters.

What does the Within Sum of Squares measure in Ward's clustering?

• The number of points in a cluster.

• The increase in variance when clusters are merged.

• The average distance between points in a cluster.

• The total distance between all points in a cluster.

What is the centroid of cluster C1 = {A, C, E}?

• (4, 5, 6)

• (5, 6.6, 4.8)

• (5.5, 7, 5.5)

• (4.67, 6.33, 4.33)

What is the increase in Within Sum of Squares when clusters C1 and C2 are merged?

• 2.998

• 5.123

• 3.456

• 1.234

Which linkage method is typically used with Ward's clustering?

• Centroid linkage.

• Average linkage.

• Complete linkage.

• Single linkage.

What does the Lance-Williamson formula assume about the clusters?

• They are independent.

• They are disjoint.

• One cluster is a union of two smaller clusters.

• They have equal sizes.

In the context of Ward's clustering, what does SSC1 represent?

• The centroid of cluster C1.

• The distance between clusters.

• The total number of clusters.

• The sum of squared distances for cluster C1.

What is the primary characteristic of the Lance-Williamson formula?

• It cannot be used for clustering.

• It is a non-recursive formula.

• It is a recursive type formula.

• It only applies to single linkage.