MGT 6203 DATA ANALYTICS
FOR MANAGEMENT MIDTERM EXAM
2026/2027
75 Multiple-Choice, Calculation-Based & Scenario Questions
Complete Questions, Correct Answers & Verified Rationales
Aligned with MGT 6203 Midterm Curriculum, AACSB Analytics Competencies
,1. Which data type is characterized by a fixed schema, organized in rows and
columns, and easily queried using SQL?
A. Unstructured data (e.g., social media posts, images)
B. Structured data (e.g., relational databases, spreadsheets)
C. Semi-structured data (e.g., JSON, XML files)
D. Streaming data (e.g., IoT sensor feeds)
Rationale: Structured data follows a predefined schema with organized rows and columns,
making it easily stored, queried, and analyzed using tools like SQL. Relational databases and
spreadsheets are classic examples. Unstructured data lacks a predefined format (images, video,
text). Semi-structured data contains tags or markers (JSON, XML) that separate elements but
do not conform to a rigid schema. Understanding data types is fundamental because the choice
of analytical tools and techniques depends heavily on the underlying data structure.
2. A marketing dataset contains customer names with inconsistent formatting (e.g.,
'J. Smith,' 'John Smith,' 'SMITH, JOHN'). This is primarily a failure of which data
quality dimension?
A. Accuracy
B. Completeness
C. Consistency
D. Timeliness
Rationale: Consistency refers to the degree to which data values are uniform and non-
contradictory across a dataset or between multiple systems. Inconsistent formatting of the same
entity across records creates analytical challenges, as grouping, filtering, and joining
operations may fail to recognize matching records. Data cleansing techniques such as
standardization, parsing, and deduplication address consistency issues. While accuracy
(correctness of values), completeness (absence of missing values), and timeliness (currency of
data) are also critical quality dimensions, this scenario specifically exemplifies a consistency
problem.
3. Data governance establishes which of the following organizational capabilities?
A. Only the technical infrastructure for data storage
B. The policies, standards, roles, and processes that ensure data is managed as a
strategic asset with appropriate quality, security, and compliance
C. The exclusive authority of IT departments over all business data
D. The process of physically securing servers in data centers
Rationale: Data governance is the overarching framework of policies, standards, roles (data
stewards, data owners), processes, and metrics that ensures an organization's data is managed
as a trusted strategic asset. It encompasses data quality management, data security and
privacy compliance, metadata management, data lifecycle management, and accountability
structures. Effective data governance bridges business and IT by defining who is responsible for
data decisions, how data quality is measured, and what policies govern data access and usage.
Without governance, analytics initiatives risk producing unreliable or non-compliant insights.
4. A retail company collects transaction records from its point-of-sale system
(internal) and purchases demographic data from a third-party provider (external).
Which statement best describes the relative advantage of internal data?
A. Internal data is always more accurate than external data
B. Internal data is typically more relevant, specific, and timely for the
organization's operational context, though it may be limited in scope
C. External data is always preferable because it provides broader market context
D. Internal data has no limitations compared to external data
Rationale: Internal data generated from an organization's own operations (transactions, CRM
systems, website analytics) is typically more relevant, specific, and timely for answering
questions about that organization's performance and customers. However, internal data is
, often limited in scope—it captures only the organization's interactions and may miss broader
market trends, competitor actions, or macroeconomic factors. External data (census data,
industry reports, social media) provides broader context but may be less directly applicable, less
timely, or require more validation. Effective analytics strategies combine both internal and
external data sources.
5. Which data quality dimension is MOST critical when analyzing real-time stock
trading data for algorithmic trading decisions?
A. Completeness
B. Timeliness
C. Consistency of formatting
D. Historical depth of records
Rationale: Timeliness—the degree to which data is current and available within the required
timeframe—is the most critical quality dimension for real-time analytics. In algorithmic
trading, decisions must be made in milliseconds using the most current market data. Even
seconds of latency can render data worthless for trading purposes. While completeness,
consistency, and historical depth are valuable for other analytical tasks, they are subordinate to
timeliness in real-time contexts. Data pipelines for real-time analytics must minimize latency
through streaming architectures, in-memory processing, and optimized data ingestion.
6. Semi-structured data differs from structured data in which fundamental way?
A. Semi-structured data cannot be analyzed by any automated tools
B. Semi-structured data does not conform to a rigid, predefined schema but
contains organizational markers such as tags or hierarchies
C. Semi-structured data is always smaller in volume than structured data
D. Semi-structured data cannot be stored in modern databases
Rationale: Semi-structured data (JSON, XML, NoSQL documents) does not conform to a rigid,
predefined tabular schema like structured data, but it contains embedded organizational
markers—tags, attributes, hierarchies—that provide some structure. This flexibility allows semi-
structured data to accommodate variable fields and nested relationships. Modern analytics
tools including NoSQL databases, JSON parsers, and schema-on-read platforms can process
semi-structured data effectively. The rise of semi-structured data has driven adoption of flexible
data platforms such as MongoDB, Elasticsearch, and data lakes that can handle diverse data
formats.
7. An organization discovers that 15% of customer email addresses in its CRM
database are invalid or undeliverable. This represents a deficiency primarily in
which data quality dimension?
A. Timeliness
B. Accuracy
C. Consistency
D. Accessibility
Rationale: Accuracy refers to the correctness and validity of data values. Invalid or
undeliverable email addresses are inaccurate data points that directly impact marketing
campaign effectiveness, customer communication, and analytics reliability. Accuracy issues
often stem from data entry errors, lack of validation rules at collection points, customer changes
not being captured, and data decay over time. Addressing accuracy requires input validation
rules, periodic data verification (e.g., email validation services), and correction workflows.
Organizations should measure accuracy as a percentage of valid, verified records within critical
data fields.
8. A data analyst receives a dataset with 500,000 rows but discovers that 40,000
rows contain missing values in critical fields. Which approach is generally
considered BEST for handling this situation?
A. Delete all rows with any missing values without analysis
FOR MANAGEMENT MIDTERM EXAM
2026/2027
75 Multiple-Choice, Calculation-Based & Scenario Questions
Complete Questions, Correct Answers & Verified Rationales
Aligned with MGT 6203 Midterm Curriculum, AACSB Analytics Competencies
,1. Which data type is characterized by a fixed schema, organized in rows and
columns, and easily queried using SQL?
A. Unstructured data (e.g., social media posts, images)
B. Structured data (e.g., relational databases, spreadsheets)
C. Semi-structured data (e.g., JSON, XML files)
D. Streaming data (e.g., IoT sensor feeds)
Rationale: Structured data follows a predefined schema with organized rows and columns,
making it easily stored, queried, and analyzed using tools like SQL. Relational databases and
spreadsheets are classic examples. Unstructured data lacks a predefined format (images, video,
text). Semi-structured data contains tags or markers (JSON, XML) that separate elements but
do not conform to a rigid schema. Understanding data types is fundamental because the choice
of analytical tools and techniques depends heavily on the underlying data structure.
2. A marketing dataset contains customer names with inconsistent formatting (e.g.,
'J. Smith,' 'John Smith,' 'SMITH, JOHN'). This is primarily a failure of which data
quality dimension?
A. Accuracy
B. Completeness
C. Consistency
D. Timeliness
Rationale: Consistency refers to the degree to which data values are uniform and non-
contradictory across a dataset or between multiple systems. Inconsistent formatting of the same
entity across records creates analytical challenges, as grouping, filtering, and joining
operations may fail to recognize matching records. Data cleansing techniques such as
standardization, parsing, and deduplication address consistency issues. While accuracy
(correctness of values), completeness (absence of missing values), and timeliness (currency of
data) are also critical quality dimensions, this scenario specifically exemplifies a consistency
problem.
3. Data governance establishes which of the following organizational capabilities?
A. Only the technical infrastructure for data storage
B. The policies, standards, roles, and processes that ensure data is managed as a
strategic asset with appropriate quality, security, and compliance
C. The exclusive authority of IT departments over all business data
D. The process of physically securing servers in data centers
Rationale: Data governance is the overarching framework of policies, standards, roles (data
stewards, data owners), processes, and metrics that ensures an organization's data is managed
as a trusted strategic asset. It encompasses data quality management, data security and
privacy compliance, metadata management, data lifecycle management, and accountability
structures. Effective data governance bridges business and IT by defining who is responsible for
data decisions, how data quality is measured, and what policies govern data access and usage.
Without governance, analytics initiatives risk producing unreliable or non-compliant insights.
4. A retail company collects transaction records from its point-of-sale system
(internal) and purchases demographic data from a third-party provider (external).
Which statement best describes the relative advantage of internal data?
A. Internal data is always more accurate than external data
B. Internal data is typically more relevant, specific, and timely for the
organization's operational context, though it may be limited in scope
C. External data is always preferable because it provides broader market context
D. Internal data has no limitations compared to external data
Rationale: Internal data generated from an organization's own operations (transactions, CRM
systems, website analytics) is typically more relevant, specific, and timely for answering
questions about that organization's performance and customers. However, internal data is
, often limited in scope—it captures only the organization's interactions and may miss broader
market trends, competitor actions, or macroeconomic factors. External data (census data,
industry reports, social media) provides broader context but may be less directly applicable, less
timely, or require more validation. Effective analytics strategies combine both internal and
external data sources.
5. Which data quality dimension is MOST critical when analyzing real-time stock
trading data for algorithmic trading decisions?
A. Completeness
B. Timeliness
C. Consistency of formatting
D. Historical depth of records
Rationale: Timeliness—the degree to which data is current and available within the required
timeframe—is the most critical quality dimension for real-time analytics. In algorithmic
trading, decisions must be made in milliseconds using the most current market data. Even
seconds of latency can render data worthless for trading purposes. While completeness,
consistency, and historical depth are valuable for other analytical tasks, they are subordinate to
timeliness in real-time contexts. Data pipelines for real-time analytics must minimize latency
through streaming architectures, in-memory processing, and optimized data ingestion.
6. Semi-structured data differs from structured data in which fundamental way?
A. Semi-structured data cannot be analyzed by any automated tools
B. Semi-structured data does not conform to a rigid, predefined schema but
contains organizational markers such as tags or hierarchies
C. Semi-structured data is always smaller in volume than structured data
D. Semi-structured data cannot be stored in modern databases
Rationale: Semi-structured data (JSON, XML, NoSQL documents) does not conform to a rigid,
predefined tabular schema like structured data, but it contains embedded organizational
markers—tags, attributes, hierarchies—that provide some structure. This flexibility allows semi-
structured data to accommodate variable fields and nested relationships. Modern analytics
tools including NoSQL databases, JSON parsers, and schema-on-read platforms can process
semi-structured data effectively. The rise of semi-structured data has driven adoption of flexible
data platforms such as MongoDB, Elasticsearch, and data lakes that can handle diverse data
formats.
7. An organization discovers that 15% of customer email addresses in its CRM
database are invalid or undeliverable. This represents a deficiency primarily in
which data quality dimension?
A. Timeliness
B. Accuracy
C. Consistency
D. Accessibility
Rationale: Accuracy refers to the correctness and validity of data values. Invalid or
undeliverable email addresses are inaccurate data points that directly impact marketing
campaign effectiveness, customer communication, and analytics reliability. Accuracy issues
often stem from data entry errors, lack of validation rules at collection points, customer changes
not being captured, and data decay over time. Addressing accuracy requires input validation
rules, periodic data verification (e.g., email validation services), and correction workflows.
Organizations should measure accuracy as a percentage of valid, verified records within critical
data fields.
8. A data analyst receives a dataset with 500,000 rows but discovers that 40,000
rows contain missing values in critical fields. Which approach is generally
considered BEST for handling this situation?
A. Delete all rows with any missing values without analysis
