cluster analysis

Question 1

what is cluster analysis

Answer 1

It allows us to simplify a mass of individual cases into fewer groups, or ‘clusters’ based on putting the most similar cases together.

Question 2

why is cluster analysis useful

Answer 2

we can then explore the characteristics of a cluster and explore the relationships between clusters and variables we might be interested in.

Question 3

cluster analysis is an analysis of ___

Answer 3

interdependence

Question 4

what is an individual variable in cluster analysis called

Answer 4

a case

Question 5

in cluster analysis what do you want to do between clusters and within clusters?

Answer 5

increase similarity between clusters and increase dissimilarity between clusters as much as possible

Question 6

what is the process of putting certain cases together based on their similarities called

Answer 6

pairing

Question 7

what are the names of the different statistical distances (how similar or dissimilar cases are) - 3

Answer 7

euclidean distances
manhattan distance
pearson distance

Question 8

what is euclidean distance?

Answer 8

square root of the sum of the squared difference between each score for two observations

Question 9

what is the most commonly used statistical distance measure

Answer 9

euclidean distance

Question 10

what is manhattan distance

Answer 10

along the corridor and up the stairs. sum of the absolute distance between score in observations

Question 11

what is an advantage of manhattan distance

Answer 11

reduces the influence of outliers

Question 12

what is pearsons distance

Answer 12

square root of the sum of squared difference between observations divided by their variance.

Question 13

what is an advantage of pearson distance

Answer 13

good for observing data that has differences in scale (different magnitude ranges)

Question 14

what is single linkage (nearest neighbor)

Answer 14

take the 2 cases that are closest together in distance, then find the next closest, etc. creating a small number of meaningful clusters

Question 15

what is complete linkage (furthest number)

Answer 15

the distance between the two clusters is based on the longest distance between any two members in the two clusters

Question 16

what is average linkage

Answer 16

The distance between the two clusters is defined as the average distance between all pairs of the two clusters’ members

Question 17

what is centroid linkage

Answer 17

the centre of each cluster is computed first. the distance between each cluster is then the distance between each centre of the cluster

Question 18

can a cluster move once it has been joined

Answer 18

no

Question 19

when are clusters specified in non heirarchal clustering

Answer 19

specified in advance

Question 20

within non hierarchical clustering do you know about the factors beforehand?

Answer 20

yes - know and understand the factors

Question 21

in non hierarchical clustering clusters are __-

Answer 21

fluid - can move up until the end of the process

Question 22

how does hierarchical clustering work

Answer 22

clusters are combined sequentially until one cluster is left (each case is a seperate cluster)

Question 23

in hierarchical clustering, clusters are ___

Answer 23

static (once a case is joined it does not move)

Question 24

wards method is associated with which form of clustering

Answer 24

hierarchical clustering

Question 25

k-means clustering is associated with which form of clustering

Answer 25

non-hierarchical

Question 26

what is ward’s method

Answer 26

uses ANOVA to evaluate the distances between clusters. looking for similarity and dissimilarity between cases and clusters

Question 27

what is k means clustering

Answer 27

an approach that produces clusters with the greatest possible distinction between clusters

Question 28

give an explanation of how wards method and k means clustering can be used in succession

Answer 28

Ward’s method to get a sense of the possible number of clusters and then k-means clustering with the optimum number of clusters used to place all the cases in those clusters.

Question 29

in a dendrogram 3 lines is equal to ___

Answer 29

3 clusters

Question 30

what method of clustering does a dendrogram start with

Answer 30

hierarchical

Question 31

what is an agglomeration schedule

Answer 31

a numerical version of a dendrogram

Question 32

what are the limitations of cluster analysis (PROAM)

Answer 32

Presence of groups does not mean they are meaningful
how many clusters to Retain
Outliers can produce clustering issues
Absence of groups does not mean they don’t exist
can have no Missing data as need to calculate distances for all cases