11 - Clustering

Question 1

Clusting is a form of…

Answer 1

unsupervised learning

Question 2

What are the 3 types of clustering algorithms?

Answer 2

1. Hierarchical
2. Partitioning
3. Mixture Models

Question 3

4 Steps for Hierarchical Clustering

Answer 3

1.
2.
3.
4.

Question 4

4 Steps for Hierarchical Clustering

Answer 4

1.
2.
3.
4.

Question 5

3 ways to recalculate distances … aka linkages

Answer 5

1. Single Linkage
2. Complete Linkage
3. Average Linkage

Question 6

Cons of Hierarchical Clustering

Answer 6

• Distance Matrices must be calculated (can be time consuming for large samples)
• results are often sensitive to what distance type & what linkage method are used

Question 7

What is K-Means Clustering

Answer 7

A clustering method that requires the user to provide the number of groups they are looking for

Question 8

What are the 4 steps of K-mean Clustering

Answer 8

1. Randomly select k (# of groups) points in your data. aka the centroids
2. Assign all observations to their closet centroid (U now have K groups)
3. Calculate the means of each group (these are the new centroids)
4. Repeat 2 & 3 until nothing changes anymore

Question 9

Pros of K-mean

Answer 9

• computationally efficient
• straightforward concept
• often provides clearer groups than HC

Question 10

Cons of K-means

Answer 10

• where the algorithm (randomly) starts can affect the results
• groups will be found no matter what, even if there are no groups present in the data