SPSS Exam Questions with Complete
Solutions
How Many Phases are in the CRISP-DM Process Methodology? - ANSWER-six
True or False: The CRISP-DM methodology is a linear process - ANSWER-False. It is a
non-linear process
True or False: The matrix node is used to examine the relationship between two
categorical variables. - ANSWER-True. And to graph it you would use a distribution
graph
Which node can be used to impute missing values? - ANSWER-Data Audit Node
Which is the standard node for displaying the relationshop between two continuous
variables? - ANSWER-Statistics Node
True or False: Only Terminal Nodes(Graphs, Modeling, Output, Export) have a Run
button as displayed in the graphic - ANSWER-True
If a field whose measurement is defined as Continuous has no value recorded, IBM
SPSS Modeler will treat it as which type of missing value? - ANSWER-Null
A prison system has historical data on prison inmates and wants to find what factors are
related to returning to prison. What type of model would be used? - ANSWER-
Classification Model
Which node is used to read data from a comma delimited text file? - ANSWER-Var. File
True or False: The optimal binning method in the Binning Node uses a supervisor field
to determine the binning cut points - ANSWER-True
True or False: Auto Checking for invalid values can be done on the type table in any
source node - ANSWER-True
Which node can be used to estimate missing values - ANSWER-Data Audit Node
Which method would be used on the merge node in order to combine a file containing
100 products and a file containing 50 supplies and retain only the matching records. -
ANSWER-Inner-Join; only matching records pass through the merge node
, True or False: To open a STREAM file you need to select the stream node from the
sources palette, place the stream node on the stream canvas, edit it, and select the
stream file. - ANSWER-False. You open a stream using File/Open from main menu
Suppose that you have
described the objectives of your data-mining project in a text document.
Furthermore, suppose you want to store this document in MODELER.
An Insurance company
has historical data on claims, such as claim amount, gender of the policy holder, age of
policy holder, claim type, number of claims in a one year
period. The company has found out that claim amount is related to number of claims
within a one year period, claim type and gender of the
policy holder. This is an example of: - ANSWER-Classification, because fraud is
predicted.
Is the following statement true or false? In the Type node, the field's role
is set in the Measurement Level column. - ANSWER-False, roles are set in the Role
column.
Is the following statement true or false? Adding an Analysis node
downstream from a TwoStep model nugget will compare the predicted
cluster membership with the actual cluster membership. - ANSWER-False. There is no
target field in segmentation models (and the Analysis node compares target fields (the
actual target field with the predicted target
field)).
What does the expression date_years_difference (DOB,
datetime_date (1, 1, 2014)) compute? (The DOB field gives the date of birth.) -
ANSWER-The expression will yield undefined ($null$) values. The datetime_date
function needs arguments year, month, and day, in that order.
Is the following statement true or false? The functions @BLANK and @NULL will
always return the same outcome. - ANSWER-False. When undefined values are not
declared as blanks, @BLANK will
return false for an undefined ($null$) value, while @NULL will return true.
Is the following statement true or false? The mean_n will return 0
when it is applied to a list of fields X1 to X4, and all these fields are
undefined. - ANSWER-False. The mean_n function will return the undefined value when
all the
source fields are undefined.
Given is an integer field X and a real field Y. What is the storage of
the field Z, which is derived as X >< Y? - ANSWER-The >< function will always return a
string field, no matter the storage of
Solutions
How Many Phases are in the CRISP-DM Process Methodology? - ANSWER-six
True or False: The CRISP-DM methodology is a linear process - ANSWER-False. It is a
non-linear process
True or False: The matrix node is used to examine the relationship between two
categorical variables. - ANSWER-True. And to graph it you would use a distribution
graph
Which node can be used to impute missing values? - ANSWER-Data Audit Node
Which is the standard node for displaying the relationshop between two continuous
variables? - ANSWER-Statistics Node
True or False: Only Terminal Nodes(Graphs, Modeling, Output, Export) have a Run
button as displayed in the graphic - ANSWER-True
If a field whose measurement is defined as Continuous has no value recorded, IBM
SPSS Modeler will treat it as which type of missing value? - ANSWER-Null
A prison system has historical data on prison inmates and wants to find what factors are
related to returning to prison. What type of model would be used? - ANSWER-
Classification Model
Which node is used to read data from a comma delimited text file? - ANSWER-Var. File
True or False: The optimal binning method in the Binning Node uses a supervisor field
to determine the binning cut points - ANSWER-True
True or False: Auto Checking for invalid values can be done on the type table in any
source node - ANSWER-True
Which node can be used to estimate missing values - ANSWER-Data Audit Node
Which method would be used on the merge node in order to combine a file containing
100 products and a file containing 50 supplies and retain only the matching records. -
ANSWER-Inner-Join; only matching records pass through the merge node
, True or False: To open a STREAM file you need to select the stream node from the
sources palette, place the stream node on the stream canvas, edit it, and select the
stream file. - ANSWER-False. You open a stream using File/Open from main menu
Suppose that you have
described the objectives of your data-mining project in a text document.
Furthermore, suppose you want to store this document in MODELER.
An Insurance company
has historical data on claims, such as claim amount, gender of the policy holder, age of
policy holder, claim type, number of claims in a one year
period. The company has found out that claim amount is related to number of claims
within a one year period, claim type and gender of the
policy holder. This is an example of: - ANSWER-Classification, because fraud is
predicted.
Is the following statement true or false? In the Type node, the field's role
is set in the Measurement Level column. - ANSWER-False, roles are set in the Role
column.
Is the following statement true or false? Adding an Analysis node
downstream from a TwoStep model nugget will compare the predicted
cluster membership with the actual cluster membership. - ANSWER-False. There is no
target field in segmentation models (and the Analysis node compares target fields (the
actual target field with the predicted target
field)).
What does the expression date_years_difference (DOB,
datetime_date (1, 1, 2014)) compute? (The DOB field gives the date of birth.) -
ANSWER-The expression will yield undefined ($null$) values. The datetime_date
function needs arguments year, month, and day, in that order.
Is the following statement true or false? The functions @BLANK and @NULL will
always return the same outcome. - ANSWER-False. When undefined values are not
declared as blanks, @BLANK will
return false for an undefined ($null$) value, while @NULL will return true.
Is the following statement true or false? The mean_n will return 0
when it is applied to a list of fields X1 to X4, and all these fields are
undefined. - ANSWER-False. The mean_n function will return the undefined value when
all the
source fields are undefined.
Given is an integer field X and a real field Y. What is the storage of
the field Z, which is derived as X >< Y? - ANSWER-The >< function will always return a
string field, no matter the storage of
