BSAN 160 Test 2 Questions with
Correct Answers
Normalizing data - Answer-reduce the range of values in each numerically valued
variable to a standard range by using a variety of normalization or scaling techniques
Discretize or aggregate data - Answer-convert the numeric variables into discrete
representations using range or frequency based binning techniques
for categorical variables, reduce the number of values by applying proper concept
hierarchies
Construct new attributes - Answer-derive new and more informative variables from the
existing ones
Method of Data Reduction - Answer-reduce the number of attributes, reduce the
number of records, and balance skewed data
Reduce number of attributes - Answer-principal component analysis, independent
component analysis, chi-square testing, correlation analysis, and decision tree induction
Reduce number of records - Answer-random sampling, stratified sampling, expert-
knowledge-driven purposeful sampling
Balance skewed data - Answer-oversample the less represented or undersample the
more represented class
Information dashboard - Answer-provide visual displays of important information that is
consolidated, cleaned, arranged on an (interactive) screen so that key insights can be
digested at a single glance and easily drilled in for further exploration
Design of storytelling dashboard - Answer-needs to set the comparative and evaluative
context
Comparative context of a storytelling dashboard - Answer-Are the number trending in
the right direction?
Use comparative measures (e.g., past values, baseline)
Evaluative context of a storytelling dashboard - Answer-Are the numbers on the
dashboard good or bad?
Visual attributes (e.g., color-coding)
visual objects (e.g., traffic lights, dials)
, Descriptive statistics - Answer-Describe the sample data at hand (central tendency
measures, spread, shape)
Inferential statistics - Answer-about drawing inferences about the characteristics of a
population using a sample from that population
Regression - Answer-used to examine the relationship between one or more
explanatory variables (input, independent) and one or more response variables (output,
dependent)
Uses of regression - Answer-forecasting values of a dependent variable (most frequent
use)
to test hypotheses
Simple linear regression - Answer-has only one input variable
Optimal line - Answer-closest to all the data points, gives the "best fit' and should
capture the trend
Regression model equation - Answer-
Multiple linear regression - Answer-one numerical dependent variable and more than
one independent variable, which can be numerical or categorical
use of a scatterplot in data assessment - Answer-visualize the relationship between
dependent and independent variables
Descriptive Analytics - Answer-What happened?
What is happening?
Predictive Analytics - Answer-What will happen?
Why will it happen?
Prescriptive Analytics - Answer-What should I do?
Why should I do it?
Compares different actions/decisions and selects the best decisions based on certain
performance criteria
When does data become information? - Answer-After it is processed
Is data absolute facts? - Answer-No, real-world data comes with uncertainty, nuances,
and biases
Structured data - Answer-organized as data arrays (e.g., spreadsheets) with variables,
observations, and values
Correct Answers
Normalizing data - Answer-reduce the range of values in each numerically valued
variable to a standard range by using a variety of normalization or scaling techniques
Discretize or aggregate data - Answer-convert the numeric variables into discrete
representations using range or frequency based binning techniques
for categorical variables, reduce the number of values by applying proper concept
hierarchies
Construct new attributes - Answer-derive new and more informative variables from the
existing ones
Method of Data Reduction - Answer-reduce the number of attributes, reduce the
number of records, and balance skewed data
Reduce number of attributes - Answer-principal component analysis, independent
component analysis, chi-square testing, correlation analysis, and decision tree induction
Reduce number of records - Answer-random sampling, stratified sampling, expert-
knowledge-driven purposeful sampling
Balance skewed data - Answer-oversample the less represented or undersample the
more represented class
Information dashboard - Answer-provide visual displays of important information that is
consolidated, cleaned, arranged on an (interactive) screen so that key insights can be
digested at a single glance and easily drilled in for further exploration
Design of storytelling dashboard - Answer-needs to set the comparative and evaluative
context
Comparative context of a storytelling dashboard - Answer-Are the number trending in
the right direction?
Use comparative measures (e.g., past values, baseline)
Evaluative context of a storytelling dashboard - Answer-Are the numbers on the
dashboard good or bad?
Visual attributes (e.g., color-coding)
visual objects (e.g., traffic lights, dials)
, Descriptive statistics - Answer-Describe the sample data at hand (central tendency
measures, spread, shape)
Inferential statistics - Answer-about drawing inferences about the characteristics of a
population using a sample from that population
Regression - Answer-used to examine the relationship between one or more
explanatory variables (input, independent) and one or more response variables (output,
dependent)
Uses of regression - Answer-forecasting values of a dependent variable (most frequent
use)
to test hypotheses
Simple linear regression - Answer-has only one input variable
Optimal line - Answer-closest to all the data points, gives the "best fit' and should
capture the trend
Regression model equation - Answer-
Multiple linear regression - Answer-one numerical dependent variable and more than
one independent variable, which can be numerical or categorical
use of a scatterplot in data assessment - Answer-visualize the relationship between
dependent and independent variables
Descriptive Analytics - Answer-What happened?
What is happening?
Predictive Analytics - Answer-What will happen?
Why will it happen?
Prescriptive Analytics - Answer-What should I do?
Why should I do it?
Compares different actions/decisions and selects the best decisions based on certain
performance criteria
When does data become information? - Answer-After it is processed
Is data absolute facts? - Answer-No, real-world data comes with uncertainty, nuances,
and biases
Structured data - Answer-organized as data arrays (e.g., spreadsheets) with variables,
observations, and values
