Cluster Analysis

Question 1

When to look at cluster patterns

Answer 1

PT would like to group patients according to their attributes in order to better treat them

PT would like to classify patients based on their individual health records in order to develop specific appropriate management strategies

Question 2

Hierarchical clustering

Answer 2

set of nested clusters organized using hierarchical tree

produce a set of nested clusters. each pair of individuals or clusters progressively nested in larger until only one remains

Question 3

Non-Hierarchical clustering

Answer 3

group of individuals into clusters so that each object is in exactly one cluster

divides a data set of ‘n’ individuals into ‘m’ clusters

K-mean clustering most commonly used type

Question 4

Hierarchical Clustering:

Bottom-up (agglomerative)

Answer 4

starts with one single piece of data and then merge it with others to form larger groups

Question 5

Hierarchical Clustering:
Top down (divisive)

Answer 5

starts with all in one group and then partition data step by step using a flat clustering algorithm

Question 6

Procedure of Agglomerative style

Answer 6

1. assign each item to a cluster
2. find closest pair of clusters and merge into a single cluster
3. compute distances (similarities) between the new cluster and each of the old clusters
4. repeat steps 2 and 3 until all items are clustered into a single cluster of the original sample size

Question 7

Limitations of Hierarchical Clustering

Answer 7

necessary to specifiy both distance metric and linkage criteria without any strong theoretical basis

selecting the number of clusters using dendrogram may mislead

Question 8

K-Mean Clustering

Answer 8

data is classified into K number of clusters.

each individual data is mapped into the cluster with its nearest mean

Question 9

K-Mean Clustering:

Procedure

Answer 9

1. select K points as initial centroids
2. assign points to different centroids based on proximity
3. re-evaluate centroid of each group
4. repeat steps 2 and 3 until best solutions emerge (centers are stable)

Question 10

K-Mean Clustering:

Limitations

Answer 10

researcher chooses number of clusters

more Ks=shorter distance from centroid

when every data point is a centroid the distance is 0 but is useless

Question 11

Two Step Clustering

Answer 11

run pre-clustering first and then hierarchical methods.

• can have categorical AND continuous clusters
• automatic selection of number of clusters
• ability to analyze large data set efficiently

Question 12

Two Step Clustering:

Procedure

Answer 12

1. a sequential approach is used to pre-cluster the cases by condensing the variables
2. the pre-clusters are statistically merged into the desired # of clusters

Question 13

Cluster Quality Validation Index:

Silhouette coefficient

Answer 13

measures how well an individual data is clustered and estimates the average distance between clusters

Question 14

Cluster Quality Validation Index:

Silhouette plot

Answer 14

displays a measure of how close each point in one cluster is to points in the neighboring cluster

Question 15

Interpretation with Silhouette coefficient:

individual data with large Silhouette coefficient value of almost 1

Answer 15

very well clustered

Question 16

Interpretation with Silhouette coefficient:

individual data with small Silhouette coefficient value of around 0

Answer 16

lies between two clusters

Question 17

Interpretation with Silhouette coefficient:

individual data with negative coefficient value

Answer 17

probably placed in the wrong cluster

Question 18

Silhouette coefficient value

0.5-1.0

Answer 18

Good

Question 19

Silhouette coefficient value

0.2-0.5

Answer 19

Fair

Question 20

Silhouette coefficient value

-1.0 - 0.2

Answer 20

Poor