Question 1

Which is best to use when selecting a clustering procedure: hierarchical or nonhierarchical clustering?

Accepted Answer

Although nonhierarchical clustering is f

Question 2

In hierarchical clustering, the solution may depend on the order of cases in the data set.

Accepted Answer

A) True 
 B)False

Question 3

It is possible to obtain information on cluster membership of cases via the icicle plot if the number of clusters is specified.

Accepted Answer

A) True 
 B)False

Question 4

Which method of analysis does not classify variables as dependent or independent?

Accepted Answer

A)  analysis of variance 
B)  regression analysis 
C)  discriminant analysis 
D)  cluster analysis 
A)  analysis of variance 
B)  regression analysis 
C)  discriminant analysis 
D)  cluster analysis

Question 5

What suggested guidelines researchers can use when deciding on the number of clusters?

Accepted Answer

Although there are no hard and fast rule

Question 6

Cluster analysis is the obverse of factor analysis in that it reduces the number of objects, not the number of variables, by grouping them into a much smaller number of clusters.

Accepted Answer

A) True 
 B)False

Question 7

In cluster analysis, the set of variables selected should describe the similarity between objects in terms that are relevant to the marketing research problem.

Accepted Answer

A) True 
 B)False

Question 8

is frequently referred to as k- means clustering.

Accepted Answer

A)  Non- hierarchical clustering 
B)  Ward's method 
C)  Agglomerative clustering 
D)  Divisive clustering 
A)  Non- hierarchical clustering 
B)  Ward's method 
C)  Agglomerative clustering 
D)  Divisive clustering

Question 9

Cluster analysis does not classify variables as dependent or independent.

Accepted Answer

A) True 
 B)False

Question 10

Which of the methods below is not a hierarchical method?

Accepted Answer

A)  parallel threshold 
B)  optimizing partitioning 
C)  variance 
D)  both A and B 
A)  parallel threshold 
B)  optimizing partitioning 
C)  variance 
D)  both A and B

Question 11

is a variance method in which the squared euclidean distance to the cluster means is minimized.

Accepted Answer

A)  Optimizing partitioning method 
B)  Sequential threshold method 
C)  Parallel threshold method 
D)  Ward's procedure 
A)  Optimizing partitioning method 
B)  Sequential threshold method 
C)  Parallel threshold method 
D)  Ward's procedure

Question 12

The TwoStep cluster analysis procedure can automatically determine the optimal number of clusters by comparing the values of a model- choice criteria across different clustering solutions.

Accepted Answer

A) True 
 B)False

Question 13

The method is based on minimum distance or the nearest neighbor rule.

Accepted Answer

A)  complete linkage 
B)  average linkage 
C)  single linkage 
D)  medium linkage 
A)  complete linkage 
B)  average linkage 
C)  single linkage 
D)  medium linkage

Question 14

In SPSS, the main program for hierarchical clustering of objects or cases is .

Accepted Answer

A)  HIERARCHICAL CLUSTER 
B)  FASTCLUS 
C)  CLUSTER ANALYSIS 
D)  VARCLUS 
A)  HIERARCHICAL CLUSTER 
B)  FASTCLUS 
C)  CLUSTER ANALYSIS 
D)  VARCLUS

Question 15

involves examining the cluster centroids.

Accepted Answer

A)  Deciding on the number of clusters 
B)  Interpreting and profiling the clusters 
C)  Assessing reliability and validity 
D)  Selecting a clustering procedure 
A)  Deciding on the number of clusters 
B)  Interpreting and profiling the clusters 
C)  Assessing reliability and validity 
D)  Selecting a clustering procedure

Question 16

Which of the following is not a procedure to check the quality of clustering results?

Accepted Answer

A)  Split the data randomly into halves. Perform clustering separately on each half. Compare cluster centroids across the two subsamples. 
B)  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. 
C)  Use the same method of clustering and compare the results. 
D)  Perform cluster analysis on the same data using different distance measures. Compare the results across measures to determine the stability of the solutions. 
A)  Split the data randomly into halves. Perform clustering separately on each half. Compare cluster centroids across the two subsamples. 
B)  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. 
C)  Use the same method of clustering and compare the results. 
D)  Perform cluster analysis on the same data using different distance measures. Compare the results across measures to determine the stability of the solutions.

Question 17

To use cluster analysis for clustering variables to identify homogeneous groups, the researcher could do all of the following except .

Accepted Answer

A)  using the correlation coefficient as a measure of similarity between variables 
B)  using the variables as the units of analysis 
C)  inserting communalities in the diagonal of the correlation matrix 
D)  both A and B 
A)  using the correlation coefficient as a measure of similarity between variables 
B)  using the variables as the units of analysis 
C)  inserting communalities in the diagonal of the correlation matrix 
D)  both A and B

Question 18

The dendrogram is read from right to left.

Accepted Answer

A) True 
 B)False

Question 19

Choice of a clustering method and choice of a distance measure are interrelated.

Accepted Answer

A) True 
 B)False

Question 20

The primary objective of cluster analysis is to classify objects into relatively homogeneous groups.

Accepted Answer

A) True 
 B)False

Exam 20: Cluster Analysis

Which is best to use when selecting a clustering procedure: hierarchical or nonhierarchical clustering?

In hierarchical clustering, the solution may depend on the order of cases in the data set.

It is possible to obtain information on cluster membership of cases via the icicle plot if the number of clusters is specified.

Which method of analysis does not classify variables as dependent or independent?

What suggested guidelines researchers can use when deciding on the number of clusters?

Cluster analysis is the obverse of factor analysis in that it reduces the number of objects, not the number of variables, by grouping them into a much smaller number of clusters.

In cluster analysis, the set of variables selected should describe the similarity between objects in terms that are relevant to the marketing research problem.

is frequently referred to as k- means clustering.

Cluster analysis does not classify variables as dependent or independent.

Which of the methods below is not a hierarchical method?

is a variance method in which the squared euclidean distance to the cluster means is minimized.

The TwoStep cluster analysis procedure can automatically determine the optimal number of clusters by comparing the values of a model- choice criteria across different clustering solutions.

The method is based on minimum distance or the nearest neighbor rule.

In SPSS, the main program for hierarchical clustering of objects or cases is .

involves examining the cluster centroids.

Which of the following is not a procedure to check the quality of clustering results?

To use cluster analysis for clustering variables to identify homogeneous groups, the researcher could do all of the following except .

The dendrogram is read from right to left.

Choice of a clustering method and choice of a distance measure are interrelated.

The primary objective of cluster analysis is to classify objects into relatively homogeneous groups.

Introduction to Marketing

Defining the Marketing Research

Research Design

Exploratory Research Design

Exploratory Research Design

Descriptive Research Design

Causal Research Design

Measurement and Scaling

Measurement and Scaling

Questionnaire and Form

Sampling: Design and

Sampling: Final and Initial

Fieldwork

Data Preparation

Frequency Distribution, Crosstabulation, and Hypothesis

Analysis of Variance and

Correlation and Regression

Discriminant and Logit

Factor Analysis

Multidimensional Scaling and

Structural Equation Modeling

Report Preparation and

International Marketing

Filters