AN 300 Practice Exam
#2 fully solved &
verified for
accuracy(guaranteed
pass)
Which of the following is FALSE about cluster analysis. Check all
that apply.
-It organizes objects into groups to minimize similarities of objects
between groups.
-It can be used to detect outliers.
-It has prior knowledge on the number of groups to be formed.
-It organizes objects into groups to maximize dissimilarities of
objects within groups.
-It organizes objects into groups to minimize dissimilarities of
objects between groups.
-It answers the "what could happen" questions.
-Its purpose is to discover natural groupings of objects of interest. -
answer -It has prior knowledge on the number of groups to be
formed.
-It organizes objects into groups to maximize dissimilarities of
objects within groups.
-It organizes objects into groups to minimize dissimilarities of
objects between groups.
-It answers the "what could happen" questions.
, the data about the object is quantitative - answer Euclidean
distance
the data about the object is qualitative - answer matching
coefficient
the similarity between two objects is the length of a straight line
between them - answer Euclidean distance
the data about the object must be standardized before calculating
the similarity measure - answer Euclidean distance
the higher the similarity measure the better - answer matching
coefficient
the number of categorical columns with matching values / total
number of categorical columns - answer matching coefficient
Which of the following is TRUE about Hierarchical Clustering? Check
all that apply.
-It generates difficult clustering results with different distance
measures.
-It only uses Matching Coefficient as a similarity measure.
-It is useful for data sets that have over 500 rows of data.
-It places each object in its own cluster when started.
-Its goodness of fit is measured by Cubic Criterion Cluster.
-It uses Ward's minimum variance only as a distance measure.
-It generates a constellation plot to visualize the clustering result in
JMP.
-It is sensitive to outliers.
#2 fully solved &
verified for
accuracy(guaranteed
pass)
Which of the following is FALSE about cluster analysis. Check all
that apply.
-It organizes objects into groups to minimize similarities of objects
between groups.
-It can be used to detect outliers.
-It has prior knowledge on the number of groups to be formed.
-It organizes objects into groups to maximize dissimilarities of
objects within groups.
-It organizes objects into groups to minimize dissimilarities of
objects between groups.
-It answers the "what could happen" questions.
-Its purpose is to discover natural groupings of objects of interest. -
answer -It has prior knowledge on the number of groups to be
formed.
-It organizes objects into groups to maximize dissimilarities of
objects within groups.
-It organizes objects into groups to minimize dissimilarities of
objects between groups.
-It answers the "what could happen" questions.
, the data about the object is quantitative - answer Euclidean
distance
the data about the object is qualitative - answer matching
coefficient
the similarity between two objects is the length of a straight line
between them - answer Euclidean distance
the data about the object must be standardized before calculating
the similarity measure - answer Euclidean distance
the higher the similarity measure the better - answer matching
coefficient
the number of categorical columns with matching values / total
number of categorical columns - answer matching coefficient
Which of the following is TRUE about Hierarchical Clustering? Check
all that apply.
-It generates difficult clustering results with different distance
measures.
-It only uses Matching Coefficient as a similarity measure.
-It is useful for data sets that have over 500 rows of data.
-It places each object in its own cluster when started.
-Its goodness of fit is measured by Cubic Criterion Cluster.
-It uses Ward's minimum variance only as a distance measure.
-It generates a constellation plot to visualize the clustering result in
JMP.
-It is sensitive to outliers.
