MIS 502: Decision Support Systems

“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―

Lecture 07: Types of Data in Cluster Analysis

MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―

Outline

• Types of data in cluster analysis

– Interval-scaled variables
– Binary variables

2
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―

Lecture Objectives
At the end of this lecture, you’ll be able to:

• Know interval-scaled variables and their applications

• Know binary variables (symmetric and asymmetric)
and their applications

3
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Interval-scaled Variables:
• They are continuous measurements of a linear scale
e.g. weight, height, temperature, coordinates of a
location.

• Changing measurement units (meters to inches or Kg

to lbs) may lead to different clustering structure.

• Standardization is needed to avoid dependence on

the choice of measurement.

4
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Interval-scaled Variables (contd..):
• Important for a multivariate analysis as variables
measured at different scales do not contribute
equally to the analysis e.g. a variable that ranges
between 0 and 100 may outweigh a variable that
ranges between 0 and 1.

• Standardizing measurements attempts to give all

variables an equal weight.

5
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Interval-scaled Variables (contd..):
• In some applications we may want to give more
weight to a certain set of variables e.g. height for the
basketball candidate players.

• Standardization may or may not be useful in a

particular application, thus the choice of whether and
how to perform standardization should be left to the
user.

• One choice of standardization is to convert the

original measurements to unitless variables.
6
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Interval-scaled Variables (contd..):
• Given measurements for a variable f , this can be performed as
follows:

• Calculate the mean absolute deviation, Sf

sf = 1
n (| x1 f − m f | + | x2 f − m f | +...+ | xnf − m f |)
• Where x1f, …., xnf are n measurements of f, and mf is the
mean value of f, i.e.
m f = 1n (x1 f + x2 f + ... + xnf ) .

Note: Using mean absolute deviation is more robust than using standard deviation.

7
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Interval-scaled Variables (contd..):

• Calculate the standard measurement or z-score:

xif − m f
zif = sf

• The dissimilarity (or similarity) between the objects

described by interval-scaled variables is typically
computed based on the distance between each pair of
objects

• Refer to Euclidean, Manhattan and Minkowski distance

measures covered earlier.
8
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables:
• A binary variable has only two states: 0 or 1, where 0
means that the variable is absent, and 1 means that it is
present.

• Given the variable allergy describing a patient,

– 1 indicates that the patient has allergy
– 0 indicates that the patient does not have it.

• Treating binary variables as if they are interval-scaled can

lead to misleading clustering results.

• Therefore, methods specific to binary data are necessary

for computing dissimilarities.
9
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (contd..):
• One approach involves computing a dissimilarity
matrix from the given binary data.

• If all binary variables are thought of as having the

same weight, we have the 2-by-2 contingency table.

10
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (contd..):

• q is the number of variables that equal 1 for both objects i and j,

• r is the number of variables that equal 1 for object i but that are 0
for object j,
• s is the number of variables that equal 0 for object i but equal 1 for
object j, and
• t is the number of variables that equal 0 for both objects i and j
• p is the total number of variables, p = q+r+s+t
11
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (symmetric):
• A binary variable is symmetric if both of its states are equally
valuable and carry the same weight
– Example: the attribute gender having the states male
and female.
• Dissimilarity that is based on symmetric binary variables is
called symmetric binary dissimilarity.
• The dissimilarity between objects i and j for symmetric binary
variables is computed as:

12
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):
• A binary variable is asymmetric if the outcomes of the states
are not equally important

– Example: the positive and negative outcomes of a HIV test.

• We shall code the most important outcome, which is usually

the rarest one, by 1 (HIV positive)

• Given two asymmetric binary variables, the agreement of two

1s (a positive match) is then considered more significant than
that of two 0s (a negative match).
13
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):
• Therefore, such binary variables are often considered
“monary”(as if having one state).

• The dissimilarity based on such variables is called asymmetric

binary dissimilarity.

• In asymmetric binary dissimilarity the number of negative

matches, t is considered unimportant and thus is ignored in
the computation:
r + s
d (i , j ) =
q+r + s
14
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):
• The asymmetric binary similarity between the objects i and j,
or sim(i, j), can be computed as:

• The coefficient sim(i, j) is called the Jaccard coefficient.

• When both symmetric and asymmetric binary variables occur

in the same data set, the mixed variables approach can be
applied (will be covered later).

15
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):
• Suppose that a patient record table contains the
attributes :
– name: an object identifier
– gender: a symmetric attribute
– fever, cough, test-1, test-2, test-3, test-4: the asymmetric
attributes

16
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):

• For asymmetric attribute values let the values Y (yes) and P

(positive) be set to1, and the value N (no or negative) be set to
0.

• Suppose that the distance between objects (patients) is

computed based only on the asymmetric variables.
17
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):

• The distance between each pair of the three patients, Jack,

Mary, and Jim, is:

18
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―
Types of Data in Cluster Analysis
Binary Variables (asymmetric):

• These measurements suggest that:

– Mary and Jim are unlikely to have a similar disease because they
have the highest dissimilarity value among the three pairs.

– Of the three patients, Jack and Mary are the most likely to have a
similar disease.
19
MIS 502: Decision Support Systems
“Don't entrust your future on others' hands. Rather make decisions by yourself with the help of God's guidance…”. Hark Herald Sarmiento
―

Thank You

20