Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Malhotra Mr05 PPT 20

Download as ppt, pdf, or txt
Download as ppt, pdf, or txt
You are on page 1of 41

Ch apter Tw enty

Cluster Analysis

© 2007 Prentice Hall 20-1


Ch apter O utl ine
1) Overview
2) Basic Concept
3) Statistics Associated with Cluster Analysis
4) Conducting Cluster Analysis
i. Formulating the Problem
ii. Selecting a Distance or Similarity Measure
iii. Selecting a Clustering Procedure
iv. Deciding on the Number of Clusters
v. Interpreting and Profiling the Clusters
vi. Assessing Reliability and Validity
© 2007 Prentice Hall 20-2
Cha pter Ou tl ine

5) Applications of Nonhierarchical Clustering

6) Clustering Variables

7) Summary

© 2007 Prentice Hall 20-3


Cl uster An al ysi s
 Cluster analysis is a class of techniques used to classify
objects or cases into relatively homogeneous groups
called clusters. Objects in each cluster tend to be
similar to each other and dissimilar to objects in the
other clusters. Cluster analysis is also called
classification analysis, or numerical taxonomy.
 Both cluster analysis and discriminant analysis are
concerned with classification. However, discriminant
analysis requires prior knowledge of the cluster or group
membership for each object or case included, to
develop the classification rule. In contrast, in cluster
analysis there is no a priori information about the group
or cluster membership for any of the objects. Groups or
clusters are suggested by the data, not defined a priori.

© 2007 Prentice Hall 20-4


An Idea l Clus tering S itu ati on

Fig. 20.1

Variable 1

Variable 2

© 2007 Prentice Hall 20-5


A Pr ac ti ca l Cl uste ri ng Situa ti on

Fig. 20.2

Variable 1

X
Variable 2

© 2007 Prentice Hall 20-6


St at is tics Asso cia ted with Clus ter
Analys is

 Ag glo me ra tio n schedu le. An agglomeration schedule


gives information on the objects or cases being combined
at each stage of a hierarchical clustering process.
 Cl ust er cen tro id . The cluster centroid is the mean
values of the variables for all the cases or objects in a
particular cluster.
 Cl ust er cen ter s. The cluster centers are the initial
starting points in nonhierarchical clustering. Clusters are
built around these centers, or seeds.
 Cl ust er memb er sh ip. Cluster membership indicates
the cluster to which each object or case belongs.

© 2007 Prentice Hall 20-7


St at is tics Asso cia ted with Clus ter
Analys is

 De ndr ogram . A dendrogram, or tree graph, is a


graphical device for displaying clustering results.
Vertical lines represent clusters that are joined together.
The position of the line on the scale indicates the
distances at which clusters were joined. The
dendrogram is read from left to right. Figure 20.8 is a
dendrogram.
 Di st an ces be tween clu st er ce nt ers . These
distances indicate how separated the individual pairs of
clusters are. Clusters that are widely separated are
distinct, and therefore desirable.

© 2007 Prentice Hall 20-8


St at is tics Asso cia ted with Clus ter
Analys is

 Ici cle dia gram . An icicle diagram is a graphical display


of clustering results, so called because it resembles a row
of icicles hanging from the eaves of a house. The
columns correspond to the objects being clustered, and
the rows correspond to the number of clusters. An icicle
diagram is read from bottom to top. Figure 20.7 is an
icicle diagram.
 Simil ari ty/d ist an ce coef ficie nt ma tri x. A
similarity/distance coefficient matrix is a lower-triangle
matrix containing pairwise distances between objects or
cases.

© 2007 Prentice Hall 20-9


Co nduc ti ng Cl us ter Ana lys is
Fig. 20.3
Formulate the Problem

Select a Distance Measure

Select a Clustering Procedure

Decide on the Number of Clusters

Interpret and Profile Clusters

Assess the Validity of Clustering

© 2007 Prentice Hall 20-10


Atti tu dina l D ata F or Cl uster ing
Table 20.1
Cas e N o. V1 V2 V3 V4 V5 V6

1 6 4 7 3 2 3
2 2 3 1 4 5 4
3 7 2 6 4 1 3
4 4 6 4 5 3 6
5 1 3 2 2 6 4
6 6 4 6 3 3 4
7 5 3 6 3 3 4
8 7 3 7 4 1 4
9 2 4 3 3 6 3
10 3 5 3 6 4 6
11 1 3 2 3 5 3
12 5 4 5 4 2 4
13 2 2 1 5 4 4
14 4 6 4 6 4 7
15 6 5 4 2 1 4
16 3 5 4 6 4 7
17 4 4 7 2 2 5
18 3 7 2 6 4 3
19 4 6 3 7 2 7
20
© 2007 Prentice Hall
2 3 2 4 7 20-11
Conduc ting Cl ust er Analy si s
For mulat e the Pro blem
 Perhaps the most important part of formulating the
clustering problem is selecting the variables on which
the clustering is based.
 Inclusion of even one or two irrelevant variables may
distort an otherwise useful clustering solution.
 Basically, the set of variables selected should describe
the similarity between objects in terms that are
relevant to the marketing research problem.
 The variables should be selected based on past
research, theory, or a consideration of the hypotheses
being tested. In exploratory research, the researcher
should exercise judgment and intuition.
© 2007 Prentice Hall 20-12
Conduc ting Cl ust er Analy si s
Se lect a D is tanc e or Sim ila ri ty Meas ure
 The most commonly used measure of similarity is the Euclidean
distance or its square. The Eu clidean dis tance is the square root
of the sum of the squared differences in values for each variable.
Other distance measures are also available. The city-block or
Manhattan distance between two objects is the sum of the absolute
differences in values for each variable. The Chebychev distance
between two objects is the maximum absolute difference in values
for any variable.
 If the variables are measured in vastly different units, the clustering
solution will be influenced by the units of measurement. In these
cases, before clustering respondents, we must standardize the data
by rescaling each variable to have a mean of zero and a standard
deviation of unity. It is also desirable to eliminate outliers (cases
with atypical values).
 Use of different distance measures may lead to different clustering
results. Hence, it is advisable to use different measures and
compare the results.
© 2007 Prentice Hall 20-13
A Cl as sif ic atio n of Cl ustering
Pr oc edure s
Fig. 20.4 Clustering Procedures

Hierarchical Nonhierarchical Other

Agglomerative Divisive Two-Step

Linkage Variance Centroid Sequential Parallel Optimizing


Methods Methods Methods Threshold Threshold Partitioning

Ward’s
Method

Single Complete Average


Linkage Linkage Linkage
© 2007 Prentice Hall 20-14
Conduc ting Cl ust er Analysi s
Se lect a C lus tering Pr oc ed ur e–
Hie rar chic al
 Hi er ar ch ica l cl us ter in g is characterized by the
development of a hierarchy or tree-like structure.
Hierarchical methods can be agglomerative or divisive.
 Ag glo mer ativ e cl ust er ing starts with each object in a
separate cluster. Clusters are formed by grouping objects
into bigger and bigger clusters. This process is continued
until all objects are members of a single cluster.
 Div isi ve clu st er ing starts with all the objects grouped
in a single cluster. Clusters are divided or split until each
object is in a separate cluster.
 Agglomerative methods are commonly used in marketing
research. They consist of linkage methods, error sums of
squares or variance methods, and centroid methods.
© 2007 Prentice Hall 20-15
Co nd uc ting Cl ust er Analy sis
Se lect a Clust ering Pro ce dur e – Link age
Met ho d
 The sin gl e l inkag e method is based on minimum
distance, or the nearest neighbor rule. At every stage, the
distance between two clusters is the distance between
their two closest points (see Figure 20.5).
 The co mp let e lin kag e method is similar to single
linkage, except that it is based on the maximum distance
or the furthest neighbor approach. In complete linkage,
the distance between two clusters is calculated as the
distance between their two furthest points.
 The aver age li nka ge method works similarly. However,
in this method, the distance between two clusters is
defined as the average of the distances between all pairs
of objects, where one member of the pair is from each of
the clusters (Figure 20.5).
© 2007 Prentice Hall 20-16
Li nka ge Met ho ds o f Cl uster ing
Fig. 20.5 Single Linkage
Minimum Distance

Cluster 1 Cluster 2
Complete Linkage
Maximum
Distance

Cluster 1 Cluster 2
Average Linkage

Average Distance
Cluster 1 Cluster 2
© 2007 Prentice Hall 20-17
Conduc ting Cl ust er Anal ysi s
Se lect a C lus tering Pr oc ed ur e – V ari anc e
Method
 The var ianc e me tho ds attempt to generate clusters to
minimize the within-cluster variance.
 A commonly used variance method is the Ward 's p roc edure .
For each cluster, the means for all the variables are computed.
Then, for each object, the squared Euclidean distance to the
cluster means is calculated (Figure 20.6). These distances are
summed for all the objects. At each stage, the two clusters with
the smallest increase in the overall sum of squares within cluster
distances are combined.
 In the cent roid me thod s, the distance between two clusters is
the distance between their centroids (means for all the variables),
as shown in Figure 20.6. Every time objects are grouped, a new
centroid is computed.
 Of the hierarchical methods, average linkage and Ward's methods
have been shown to perform better than the other procedures.
© 2007 Prentice Hall 20-18
Ot he r Agglo merat ive Cl ustering
Methods
Fig. 20.6
Ward’s Procedure

Centroid Method

© 2007 Prentice Hall 20-19


Co nd ucting Cl uster Analy sis
Se lec t a Clu steri ng Proc ed ur e–
Nonh ierarchical
 The nonh ie rarch ical clu st ering methods are frequently referred
to as k-means clustering. These methods include sequential
threshold, parallel threshold, and optimizing partitioning.
 In the se quent ia l t hre shold me thod , a cluster center is selected
and all objects within a prespecified threshold value from the center
are grouped together. Then a new cluster center or seed is selected,
and the process is repeated for the unclustered points. Once an
object is clustered with a seed, it is no longer considered for
clustering with subsequent seeds.
 The pa ralle l t hres hold m etho d operates similarly, except that
several cluster centers are selected simultaneously and objects within
the threshold level are grouped with the nearest center.
 The op tim izin g p artit ion in g meth od differs from the two
threshold procedures in that objects can later be reassigned to
clusters to optimize an overall criterion, such as average within
cluster distance for a given number of clusters.
© 2007 Prentice Hall 20-20
Co nduc ti ng Cl us ter Ana lysis
Sel ect a Cl uster ing Pro cedu re
 It has been suggested that the hierarchical and
nonhierarchical methods be used in tandem. First, an
initial clustering solution is obtained using a hierarchical
procedure, such as average linkage or Ward's. The
number of clusters and cluster centroids so obtained are
used as inputs to the optimizing partitioning method.
 Choice of a clustering method and choice of a distance
measure are interrelated. For example, squared
Euclidean distances should be used with the Ward's and
centroid methods. Several nonhierarchical procedures
also use squared Euclidean distances.

© 2007 Prentice Hall 20-21


Resu lts of H iera rc hi cal
Cl uster ing
Table 20.2

Ag glom er ation Sch edu le Us in g Wa rd’ s Procedu re


Sta ge
cl uster
Stage ClCluster
uster1s Cluster
com bin
2 edCoefficient Cluster 1firCluster
st 2 Next stage
1 appea
14 rs 16 1.000000 0 0 6
2 6 7 2.000000 0 0 7
3 2 13 3.500000 0 0 15
4 5 11 5.000000 0 0 11
5 3 8 6.500000 0 0 16
6 10 14 8.160000 0 1 9
7 6 12 10.166667 2 0 10
8 9 20 13.000000 0 0 11
9 4 10 15.583000 0 6 12
10 1 6 18.500000 6 7 13
11 5 9 23.000000 4 8 15
12 4 19 27.750000 9 0 17
13 1 17 33.100000 10 0 14
14 1 15 41.333000 13 0 16
15 2 5 51.833000 3 11 18
16 1 3 64.500000 14 5 19
17 4 18 79.667000 12 0 18
18 2 4 172.662000 15 17 19
19 1 2 328.600000 16 18 0
© 2007 Prentice Hall 20-22
Resu lts of H iera rc hi cal
Cl uster ing
Table 20.2, cont.
Cluster Membership of Cases Using Ward’s Procedure
Number of Clusters
Label case 4 3 2

1 1 1 1
2 2 2 2
3 1 1 1
4 3 3 2
5 2 2 2
6 1 1 1
7 1 1 1
8 1 1 1
9 2 2 2
10 3 3 2
11 2 2 2
12 1 1 1
13 2 2 2
14 3 3 2
15 1 1 1
16 3 3 2
17 1 1 1
18 4 3 2
19 3 3 2
20 2 2 2
© 2007 Prentice Hall 20-23
Verti cal Icicle Plo t Us ing War d’ s
Method
Fig. 20.7

© 2007 Prentice Hall 20-24


Dendr ogra m Using Wa rd’s
Meth od
Fig. 20.8

© 2007 Prentice Hall 20-25


Co nduc ti ng Cl us ter Ana lys is
Deci de o n th e Nu mbe r of
Cl uster s
 Theoretical, conceptual, or practical considerations may
suggest a certain number of clusters.
 In hierarchical clustering, the distances at which clusters
are combined can be used as criteria. This information
can be obtained from the agglomeration schedule or
from the dendrogram.
 In nonhierarchical clustering, the ratio of total within-
group variance to between-group variance can be
plotted against the number of clusters. The point at
which an elbow or a sharp bend occurs indicates an
appropriate number of clusters.
 The relative sizes of the clusters should be meaningful.
© 2007 Prentice Hall 20-26
Co nduc ti ng Cl us ter Ana lysis
Inte rpre ti ng a nd Pro fi li ng t he
Cl uster s

 Interpreting and profiling clusters involves examining


the cluster centroids. The centroids enable us to
describe each cluster by assigning it a name or label.

 It is often helpful to profile the clusters in terms of


variables that were not used for clustering. These
may include demographic, psychographic, product
usage, media usage, or other variables.

© 2007 Prentice Hall 20-27


Cl uster Cen troi ds
Table 20.3

Means of Variables

Cluster No. V1 V2 V3 V4 V5 V6

1 5.750 3.625 6.000 3.125 1.750 3.875

2 1.667 3.000 1.833 3.500 5.500 3.333

3
© 2007 Prentice Hall
3.500 5.833 3.333 6.000 3.500 6.000 20-28
Co nduc ti ng Cl ust er Ana lysis
Asse ss Reli abil ity a nd Vali di ty
1. Perform cluster analysis on the same data using different
distance measures. Compare the results across measures to
determine the stability of the solutions.
2. Use different methods of clustering and compare the results.
3. Split the data randomly into halves. Perform clustering
separately on each half. Compare cluster centroids across
the two subsamples.
4. Delete variables randomly. Perform clustering based on the
reduced set of variables. Compare the results with those
obtained by clustering based on the entire set of variables.
5. In nonhierarchical clustering, the solution may depend on
the order of cases in the data set. Make multiple runs using
different order of cases until the solution stabilizes.
© 2007 Prentice Hall 20-29
Resu lts of No nhier ar chica l
Cl uster ing
Table 20.4
Initial Cluster Centers
Cluster
1 2 3
V1 4 2 7
V2 6 3 2
V3 3 2 6
V4 7 4 4
V5 2 7 1
V6 7 2 3 a
Iteration History
Change in Cluster Centers
Iteration 1 2 3
1 2.154 2.102 2.550
2 0.000 0.000 0.000
a. Convergence achieved due to no or small distance
change. The maximum distance by which any center
has changed is 0.000. The current iteration is 2. The
minimum distance between initial centers is 7.746.
© 2007 Prentice Hall 20-30
Res ul ts o f Nonh ier ar ch ica l
Cl uster ing
Table 20.4 cont. Cluster Membership
Case Number Cluster Distance
1 3 1.414
2 2 1.323
3 3 2.550
4 1 1.404
5 2 1.848
6 3 1.225
7 3 1.500
8 3 2.121
9 2 1.756
10 1 1.143
11 2 1.041
12 3 1.581
13 2 2.598
14 1 1.404
15 3 2.828
16 1 1.624
17 3 2.598
18 1 3.555
19 1 2.154
20 2 2.102
© 2007 Prentice Hall 20-31
Resu lts of No nhier ar ch ica l
Cl uster ing
Table 20.4, cont.
Fi nal Cl ust er Cen ter s
Cluster
1 2 3
V1 4 2 6
V2 6 3 4
V3 3 2 6
V4 6 4 3
V5 4 6 2
V6 6 3 4

Dis tan ces bet wee n Fin al Clu st er Cen ter s


Cluster 1 2 3
1 5.568 5.698
2 5.568 6.928
3 5.698 6.928
© 2007 Prentice Hall 20-32
Res ul ts o f Nonh ier ar ch ica l
Cl uster ing
Table 20.4, cont.

ANOVA
Cluster Error
Mean Square df Mean Square df F Sig.
V1 29.108 2 0.608 17 47.888 0.000
V2 13.546 2 0.630 17 21.505 0.000
V3 31.392 2 0.833 17 37.670 0.000
V4 15.713 2 0.728 17 21.585 0.000
V5 22.537 2 0.816 17 27.614 0.000
V6 12.171 2 1.071 17 11.363 0.001
The F tests should be used only for descriptive purposes because the clusters have been
chosen to maximize the differences among cases in different clusters. The observed
significance levels are not corrected for this, and thus cannot be interpreted as tests of the
hypothesis that the cluster means are equal.

Number of Cases in each Cluster


Cluster 1 6.000
2 6.000
3 8.000
Valid 20.000
Missing 0.000
© 2007 Prentice Hall 20-33
Res ul ts o f Two -S tep Cl uster ing
Table 20.5 Auto-Clustering

Akaike's Ratio of
Information AIC Ratio of AIC Distance
Number of Clusters Criterion (AIC) Change(a) Changes(b) Measures(c)
1 104.140
2 101.171 -2.969 1.000 .847
3 97.594 -3.577 1.205 1.583
4 116.896 19.302 -6.502 2.115
5 138.230 21.335 -7.187 1.222
6 158.586 20.355 -6.857 1.021
7 179.340 20.755 -6.991 1.224
8 201.628 22.288 -7.508 1.006
9 224.055 22.426 -7.555 1.111
10 246.522 22.467 -7.568 1.588
11 269.570 23.048 -7.764 1.001
12 292.718 23.148 -7.798 1.055
13 316.120 23.402 -7.883 1.002
14 339.223 23.103 -7.782 1.044
15 362.650 23.427 -7.892 1.004
a The changes are from the previous number of clusters in the table.
b The ratios of changes are relative to the change for the two cluster solution.
c The ratios of distance measures are based on the current number of clusters
against the previous number of clusters.
© 2007 Prentice Hall 20-34
Cl uster Distri bu ti on
Table 20.5, cont.

% of
N Combined % of Total
Cluster 1 6 30.0% 30.0%
2 6 30.0% 30.0%
3 8 40.0% 40.0%
Combined 20 100.0% 100.0%
Total 20 100.0%

© 2007 Prentice Hall 20-35


Cl uster Profi les
Table 20.5, cont.

Fun Bad for Budget Eating Out


Mean Std. Deviation Mean Std. Deviation Mean Std. Deviation
Cluster 1 1.67 .516 3.00 .632 1.83 .753
2 3.50 .548 5.83 .753 3.33 .816
3 5.75 1.035 3.63 .916 6.00 1.069
Combined 3.85 1.899 4.10 1.410 3.95 2.012

Best Buys Don't Care Compare Prices


Mean Std. Deviation Mean Std. Deviation Mean Std. Deviation
3.50 1.049 5.50 1.049 3.33 .816
6.00 .632 3.50 .837 6.00 1.549
3.13 .835 1.88 .835 3.88 .641
4.10 1.518 3.45 1.761 4.35 1.496

© 2007 Prentice Hall 20-36


Cl uster ing V ar iables
 In this instance, the units used for analysis are the
variables, and the distance measures are computed for all
pairs of variables.
 Hierarchical clustering of variables can aid in the
identification of unique variables, or variables that make a
unique contribution to the data.
 Clustering can also be used to reduce the number of
variables. Associated with each cluster is a linear
combination of the variables in the cluster, called the
cluster component. A large set of variables can often be
replaced by the set of cluster components with little loss of
information. However, a given number of cluster
components does not generally explain as much variance
as the same number of principal components.
© 2007 Prentice Hall 20-37
SP SS Wi ndow s

To select this procedures using SPSS for Windows


click:

An aly ze> Cl as sif y>H ie rar chi cal Cl ust er …

An aly ze> Cl as sif y>K -Mea ns Clus te r …

An aly ze> Cl as sif y>T wo -St ep Cl ust er …

© 2007 Prentice Hall 20-38


SPSS W indo ws: Hiera rc hic al Clus teri ng
1. Select ANALYZE from the SPSS menu bar.
2. Click CLASSIFY and then HIERARCHICAL CLUSTER.
3. Move “Fun [v1],” “Bad for Budget [v2],” “Eating Out [v3],” “Best Buys [v4],”
“Don’t Care [v5],” and “Compare Prices [v6].” in to the VARIABLES box.
4. In the CLUSTER box check CASES (default option). In the DISPLAY box
check STATISTICS and PLOTS (default options).
5. Click on STATISTICS. In the pop-up window, check AGGLOMERATION
SCHEDULE. In the CLUSTER MEMBERSHIP box check RANGE OF
SOLUTIONS. Then, for MINIMUM NUMBER OF CLUSTERS: enter 2 and for
MAXIMUM NUMBER OF CLUSTERS enter 4. Click CONTINUE.
6. Click on PLOTS. In the pop-up window, check DENDROGRAM. In the
ICICLE box check ALL CLUSTERS (default). In the ORIENTATION box, check
VERTICAL. Click CONTINUE.
7. Click on METHOD. For CLUSTER METHOD select WARD’S METHOD. In the
MEASURE box check INTERVAL and select SQUARED EUCLIDEAN DISTANCE.
Click CONTINUE
8. Click OK.
© 2007 Prentice Hall 20-39
SP SS Wi ndow s: K -Mea ns Cl uste ri ng

1. Select ANALYZE from the SPSS menu bar.


2. Click CLASSIFY and then K-MEANS CLUSTER.
3. Move “Fun [v1],” “Bad for Budget [v2],” “Eating Out
[v3],” “Best Buys [v4],” “Don’t Care [v5],” and “Compare
Prices [v6].” in to the VARIABLES box.
4. For NUMBER OF CLUSTER select 3.
5. Click on OPTIONS. In the pop-up window, In the
STATISTICS box, check INITIAL CLUSTER CENTERS and
CLUSTER INFORMATION FOR EACH CASE. Click
CONTINUE.
6. Click OK.
© 2007 Prentice Hall 20-40
SP SS Wi ndow s: Two -S tep
Cl uster ing
1. Select ANALYZE from the SPSS menu bar.
2. Click CLASSIFY and then TWO-STEP CLUSTER.
3. Move “Fun [v1],” “Bad for Budget [v2],” “Eating Out
[v3],” “Best Buys [v4],” “Don’t Care [v5],” and “Compare
Prices [v6].” in to the CONTINUOUS VARIABLES box.
4. For DISTANCE MEASURE select EUCLIDEAN.
5. For NUMBER OF CLUSTER select DETERMINE
AUTOMATICALLY.
6. For CLUSTERING CRITERION select AKAIKE’S
INFORMATION CRITERION (AIC).
7. Click OK.
© 2007 Prentice Hall 20-41

You might also like