37 free CompTIA Data+ DA0-002 practice questions from the CertStash pack of 148, each with the correct answer and a full explanation. The rule is the same for every exam: ten free on the product page, 37 free here, all 148 in the pack, and each step includes the one before it.
Get all 148 questions (US$39) · Download the first 10 as a PDF · Read the study guide
Question 1
Which of the following makes data unreadable without a required key?
Show answer and explanation
Correct answer: C. Encryption
Encryption is the process of converting readable data into an unreadable format using a cryptographic key, making it inaccessible without the correct decryption key. Anonymization removes identifying information but doesn't make data unreadable. Role-based access control restricts who can access data but doesn't render it unreadable. Masking obscures data for display purposes but doesn't fundamentally make it unreadable to those with access.
Why the other options are wrong
- A. Anonymization removes identifiers but leaves data in a readable format.
- B. RBAC controls access permissions but doesn't make data unreadable.
- D. Masking hides data visually but doesn't prevent reading by authorized users.
Question 2
An analyst is building a reporting deck. The deck must include tracking and visualizing metrics and row-level security. Which of the following actions should the analyst take after meeting the initial requirements?
Show answer and explanation
Correct answer: A. Show a mock-up to the team.
After identifying initial requirements like tracking metrics and row-level security, the next logical step is to validate assumptions and gather feedback by showing a mock-up to the team. This allows stakeholders to visualize the solution, provide feedback, and ensure the analyst's understanding of requirements is correct before investing significant effort in full development.
Why the other options are wrong
- B. Explaining reporting detail should happen during initial requirements gathering, not after.
- C. Presenting analysis is a later deliverable, not a follow-up to initial requirements.
- D. Finding the due date should be established before or during initial requirements, not after.
Question 3
Which of the following pieces of information, if made public, results in a data privacy violation?
Show answer and explanation
Correct answer: B. Driver’s license
A driver's license number is personally identifiable information (PII) that directly identifies an individual and is regulated under privacy laws. Public disclosure would constitute a clear data privacy violation. Gender, age, and employment status, while sensitive, are demographic attributes that alone do not uniquely identify individuals and may be disclosed in aggregate or anonymized form without necessarily violating privacy regulations.
Why the other options are wrong
- A. Gender alone is not sufficient to identify an individual and may be disclosed in aggregate.
- C. Age alone is demographic information that doesn't uniquely identify someone.
- D. Employment status is general information that may be publicly disclosed without privacy violation.
Question 4
A data analyst needs to use one table's data to refine data selection from a second table. Which of the following is the most efficient way?
Show answer and explanation
Correct answer: A. Subquery
A subquery is the most efficient way to use one table's data to refine data selection from a second table, as it allows filtering based on conditions derived from another table in a single query operation. Joins combine tables but require matching on keys. Aggregates summarize data rather than refine selection. Unions combine results from multiple tables rather than use one to filter another.
Why the other options are wrong
- B. Aggregates summarize data; they don't refine selection based on another table.
- C. Unions combine result sets vertically; they don't filter one table by another.
- D. Joins combine tables horizontally but may not be more efficient than a subquery for this specific task.
Question 5
Which of the following is found in metadata?
Show answer and explanation
Correct answer: B. Data lineage
Data lineage, which tracks the origin and flow of data through systems and transformations, is a key component of metadata. It documents how data moves and changes throughout the data pipeline. Transformations are data operations, not metadata. Syntax refers to code structure, not metadata. Variable types are data properties but are distinct from the lineage aspect that defines metadata.
Why the other options are wrong
- A. Transformations are operations on data, not metadata about data.
- C. Syntax is the structure of code, not metadata describing data.
- D. While metadata can include type information, data lineage is the more comprehensive metadata element.
Question 6
Which of the following allows the transfer of isolated applications to multiple environments?
Show answer and explanation
Correct answer: D. Containerization
Containerization packages applications with their dependencies into isolated containers that can run consistently across multiple environments, enabling seamless transfer and deployment. Virtualization creates virtual machines but is heavier-weight than containers. Version control tracks code changes but doesn't directly enable application transfer. Continuous integration automates testing and merging but doesn't isolate applications for multi-environment deployment.
Why the other options are wrong
- A. Virtualization creates VMs but is less efficient than containerization for this purpose.
- B. Version control manages code versions but doesn't package applications for deployment.
- C. Continuous integration automates builds and testing, not application environment transfer.
Question 7
A data breach occurs at a company. Which of the following actions should be taken?
Show answer and explanation
Correct answer: B. Tell the company management team and then tell regulatory agencies.
The proper incident response procedure is to first notify management and then inform regulatory agencies as required by law. This follows the appropriate chain of command and legal obligations. Social media announcements bypass proper notification channels. Keeping breaches secret violates disclosure laws. Informing the IT sector broadly is not standard protocol and spreads sensitive information unnecessarily.
Why the other options are wrong
- A. Announcing on social media bypasses proper internal and regulatory notification.
- C. Hiding breaches violates privacy laws and regulatory requirements.
- D. Informing the IT sector at large is not protocol and spreads sensitive information unnecessarily.
Question 8
A data analyst is modeling a new data warehouse to analyze sales. One of the requirements is to analyze sales by region. Which of the following best describes the region table?
Show answer and explanation
Correct answer: B. Dimensional
A region table is a dimensional table in a data warehouse schema. Dimensional tables contain descriptive attributes used to analyze facts and support filtering and grouping operations, such as analyzing sales by region. Fact tables contain quantitative measures and foreign keys. Bridge tables resolve many-to-many relationships. Snowflake refers to a schema design pattern, not a table type.
Why the other options are wrong
- A. Fact tables contain measures and metrics, not descriptive attributes like region.
- C. Bridge tables resolve many-to-many relationships, not dimensional analysis.
- D. Snowflake is a schema design pattern, not a classification for this specific table.
Question 9
Which of the following data repositories stores unformatted data in its original, raw form?
Show answer and explanation
Correct answer: D. Data lake
A data lake is a centralized repository designed to store large volumes of unformatted, raw data in its original form without preprocessing or transformation. Unlike data warehouses (structured), data marts (curated subsets), or data silos (isolated systems), data lakes preserve raw data exactly as ingested, allowing flexible analysis and later refinement.
Why the other options are wrong
- A. Data warehouses store processed, structured, and formatted data, not raw unformatted data.
- B. Data silos are isolated repositories within departments, not comprehensive raw data repositories.
- C. Data marts contain curated, organized subsets of data intended for specific business functions, not raw unformatted data.
Question 10
A data analyst must combine service calls into low-, medium-, and high-priority levels in order to analyze organizational responses. Which of the following techniques should the analyst use for this task?
Show answer and explanation
Correct answer: D. Binning
Binning is the technique of grouping continuous or discrete data values into categories or bins, in this case, service calls into low, medium, and high priority levels. This converts raw values into meaningful categorical groups for analysis and organizational response evaluation.
Why the other options are wrong
- A. Augmentation involves adding new features or data to expand datasets, not categorizing existing values.
- B. Imputation fills missing data values, not groups existing data into priority categories.
- C. Scaling normalizes data to a specific range, not organizes data into meaningful priority classifications.
What people say about the full DA0-002 pack 5.0 from 1
Results came in, I passed! Will keep using this for future certs.
Question 11
A data company needs a visualization that shows the availability zones from the last ten years and any future availability zones that the company will be using in the next five years. Which of the following is the most appropriate visualization to display this information?
Show answer and explanation
Correct answer: C. Map
Availability zones are geographical locations associated with cloud infrastructure, making this fundamentally a geographical/spatial visualization problem. A map is the most appropriate visualization for displaying locations across time periods (past availability zones and future planned zones), as it naturally represents geographical distribution and can use time-based annotations or overlays to show historical versus projected zones.
Why the other options are wrong
- A. A bar chart is better for comparing discrete values or categories over time, not for showing geographical distribution of zones.
- B. A mosaic plot is designed for showing relationships between categorical variables, not geographical locations.
- D. A pie chart shows part-to-whole relationships and is poor for temporal or geographical comparisons.
Question 12
A data analyst is preparing a survey for Paralympic Game athletes. Which of the following should the analyst consider when creating this survey?
Show answer and explanation
Correct answer: B. Color contrast
Color contrast is critical for accessibility, especially for athletes with visual impairments, color blindness, or low vision. Proper color contrast ensures that all respondents can read and complete the survey effectively.
Why the other options are wrong
- A. Idioms are a language consideration but are less critical than visual accessibility for this specific audience.
- C. Refresh speed relates to system performance, not survey design or accessibility.
- D. Granularity relates to data detail level, not survey accessibility considerations.
Question 13
A manager requests a report that returns results based on a user’s profile. Which of the following best describes this type of report?
Show answer and explanation
Correct answer: C. Dynamic
A dynamic report generates results based on parameters or user inputs, such as a profile, and delivers different output depending on those variables. This is the defining characteristic of dynamic reporting, the content changes based on the criteria supplied by the user. A user profile is a perfect example of a parameter that would drive dynamic report generation.
Why the other options are wrong
- A. Real-time reports focus on timeliness of data, not on personalization based on user profiles.
- B. Static reports deliver the same fixed content to all users regardless of profile or preferences.
- D. Snapshot reports capture data at a specific point in time, not based on user-specific profiles or parameters.
Question 14
Which of the following programming languages are the most efficient at performing data mining and statistical analysis? (Choose two.)
Show answer and explanation
Correct answer: B, C. R; Python
R and Python are the two most widely used and efficient programming languages specifically designed for data mining and statistical analysis. R provides extensive built-in statistical functions and libraries (ggplot2, dplyr, etc.), while Python offers powerful data science libraries (pandas, scikit-learn, NumPy, SciPy). Both dominate the data science field and are optimized for these tasks.
Why the other options are wrong
- A. Java is general-purpose and not specifically optimized for statistical analysis, though it can be used for data engineering.
- D. Ruby is a general-purpose scripting language without strong built-in statistical or data mining capabilities.
- E. Julia is a newer language for numerical computing, not as established or widely adopted as R and Python for data mining.
- F. C++ is a systems language best for performance-critical applications, not for statistical analysis where development speed matters.
Question 15
A data analyst troubleshoots a dashboard every day for a week. Which of the following techniques best addresses how to validate the data moving forward?
Show answer and explanation
Correct answer: B. Setting up monitoring alerts
Setting up monitoring alerts provides ongoing automated validation of data quality and catches issues before they impact the dashboard, preventing the need for daily troubleshooting. This is a proactive, scalable approach to validation.
Why the other options are wrong
- A. Inquiring about structure changes is reactive and does not validate existing data moving forward.
- C. Reaching out to users daily is inefficient and does not address systematic data validation.
- D. Rebuilding the dashboard is resource-intensive and does not prevent future issues.
Question 16
A data analyst is creating a pivot table for a large data set for an upcoming board meeting. Which of the following is the purpose of the pivot table?
Show answer and explanation
Correct answer: C. To summarize and analyze the data
A pivot table is specifically designed to summarize, aggregate, and analyze large data sets by reorganizing and grouping data to reveal patterns and insights. This is its primary purpose before presentation.
Why the other options are wrong
- A. Visualization in dashboards uses pivot tables as input but is not the pivot table's own purpose.
- B. Data retrieval and cleaning are preprocessing steps that happen before pivot table creation.
- D. Organization for reporting is a secondary benefit; the primary purpose is analysis and summarization.
Question 17
A manager wants a report that contains the days off for each direct report. The manager needs this report to always be up-to-date with the latest data. Which of the following describes the refresh frequency that the manager is requesting?
Show answer and explanation
Correct answer: A. Real-time
Real-time refresh frequency ensures that the report is always up-to-date with the latest data, updating continuously or near-instantaneously as data changes. This meets the manager's requirement for the report to always reflect current employee time-off information.
Why the other options are wrong
- B. Ad hoc refresh occurs only when manually requested, not continuously.
- C. Snapshot refresh captures data at a single point in time and does not update automatically.
- D. Dynamic refers to interactive elements in reports, not the frequency of data updates.
Question 18
A sales manager wants a dashboard that shows sales aggregated by region and identifies high-volume sales by salesperson per region. Which of the following techniques best displays this information?
Show answer and explanation
Correct answer: C. Level of detail
Level of detail (LOD) is a technique that controls the granularity of data aggregation within visualizations, allowing analysts to show data at different levels simultaneously. To display sales aggregated by region AND identify high-volume sales by individual salesperson within those regions, LOD expressions permit aggregation at multiple hierarchical levels within a single visualization.
Why the other options are wrong
- A. Defined parameters allow users to control variable values but don't inherently enable multi-level aggregation within a single view.
- B. Filter options let users select subsets of data but don't address the core requirement of displaying simultaneous aggregation levels.
- D. User personas are audience profiles used in design planning, not technical visualization techniques for displaying multi-level data.
Question 19
A database administrator is attempting to load a set of database logs into a software system. Upon processing the data, the administrator receives a notification that this process failed because the data size is too large for the system memory. Which of the following is the best way for the administrator to correct this issue?
Show answer and explanation
Correct answer: C. Perform chunking on the data.
Chunking divides large data sets into smaller, manageable pieces that can be processed sequentially without exceeding memory limits. This is the standard technique for handling large-scale data processing and allows the system to work within its constraints. It's more practical than simply increasing memory size and addresses the root cause rather than just throwing more resources at the problem.
Why the other options are wrong
- A. Internal storage doesn't solve the memory overflow issue; data still needs to be loaded into memory for processing.
- B. Analyzing logs for errors is unrelated to the memory capacity problem preventing data loading.
- D. While increasing memory could work, it's not the most efficient solution and may be costly or impractical; chunking is the best practice approach.
Question 20
A data analyst needs to provide a weekly sales report for the Chief Financial Officer. Which of the following delivery methods is the most appropriate?
Show answer and explanation
Correct answer: D. A high-level email
A high-level email is most appropriate for a CFO receiving a weekly sales report because executives need concise, actionable summaries rather than granular details. This delivery method respects the executive's time constraints and focuses on key insights. Detailed raw data and granular dashboards are better suited for analysts working with the data directly, not summary reporting to leadership.
Why the other options are wrong
- A. A granular daily report in a dashboard provides too much detail and updates too frequently for executive summary purposes.
- B. A detailed text document is unnecessarily verbose for executive communication; executives prefer high-level summaries.
- C. Raw data in a spreadsheet requires the CFO to analyze and interpret data themselves rather than receiving actionable insights.
Question 21
A data analyst is preparing a report for external users. The analyst must ensure that visuals can be identified as belonging to the organization. Which of the following should the analyst add to the report to best meet this requirement?
Show answer and explanation
Correct answer: D. Watermark
A watermark is a visible marker or logo overlaid on report visuals that clearly identifies ownership and belonging to the organization. Watermarks serve as a branding and security measure to ensure external viewers recognize the visual as organizational property.
Why the other options are wrong
- A. Legal disclaimers address liability and terms, not organizational identification of visuals.
- B. Infographics present information visually but do not specifically identify organizational ownership.
- C. Subtitles provide additional context or description, not organizational branding or identification.
Question 22
A company’s analytics manager wants all reports to be delivered once every seven days. Which of the following is the best delivery method?
Show answer and explanation
Correct answer: A. Recurring
Recurring delivery is designed for reports that need to be sent on a fixed schedule, in this case, every seven days. This is the standard terminology and method for automated, scheduled report distribution that repeats at regular intervals.
Why the other options are wrong
- B. Ad hoc delivery means on-demand or one-time reports, not scheduled repeating delivery.
- C. Custom refers to tailored report configurations, not the delivery method or scheduling mechanism.
- D. Snapshot typically refers to a point-in-time capture of data, not a delivery frequency or method.
Question 23
A data analyst is gathering data from multiple tables in a database. The analyst needs certain columns from each table. Which of the following is the best method to accomplish this task?
Show answer and explanation
Correct answer: D. Join
A JOIN operation combines rows from multiple tables based on related columns, allowing the analyst to retrieve specific columns from different tables in a single query. This is the standard SQL method for accessing data from multiple tables while selecting only the needed columns.
Why the other options are wrong
- A. Aggregate functions (SUM, COUNT, etc.) perform calculations on data but don't retrieve columns from multiple tables.
- B. UNION combines result sets from multiple queries with the same columns, not for selecting specific columns from different tables.
- C. Nesting refers to subqueries or nested structures, which is less efficient than JOIN for combining data from multiple tables.
Question 24
A data engineer needs to create a reporting solution that has predefined filters and the ability to download .csv files. Which of the following is the best solution?
Show answer and explanation
Correct answer: C. Creating a self-service portal on the company's intranet
A self-service portal on the company intranet provides both predefined filters for easy access and the capability to download data in CSV format, meeting both requirements. It's also the most scalable solution allowing multiple users to independently generate reports without analyst intervention. The other options either lack filtering capability, CSV download functionality, or don't provide self-service access.
Why the other options are wrong
- A. A dynamic dashboard with daily refresh doesn't inherently provide CSV download capability or flexible self-service filtering.
- B. A weekly executive summary is a push approach that lacks self-service filtering and download options.
- D. An email template for requesting ad hoc reports is not self-service; it requires analyst involvement for each request.
Question 25
A data analyst is querying a database. However, the analyst is unfamiliar with the table names, field names, data types, and field definitions. Which of the following is the best place to look for this information?
Show answer and explanation
Correct answer: A. Data dictionary
A data dictionary is specifically designed to document table names, field names, data types, field definitions, and other metadata about a database schema. It is the standard reference document for understanding database structure and is exactly what an analyst needs when unfamiliar with a database. A data dictionary provides comprehensive information about what data exists and how it is defined.
Why the other options are wrong
- B. A data explainability report focuses on model interpretability and insights, not database schema documentation.
- C. Data lineage shows how data flows and transforms through systems, not table and field definitions.
- D. A data flow diagram shows process flows and data movement between systems, not detailed field-level metadata and definitions.
Question 26
A data analyst receives a flat file that includes dates. The analyst needs to calculate the number of days from the dates on the file to the current date. Which of the following is the best way to complete this task?
Show answer and explanation
Correct answer: A. Convert data to date format and use date functions.
Converting data to the proper date format is the best practice before performing date calculations. Once dates are properly formatted, date functions can reliably calculate differences such as days from a specific date to today. This ensures accuracy and prevents errors from treating dates as text or numbers.
Why the other options are wrong
- B. Validating format with logical functions adds unnecessary steps; conversion is the primary requirement.
- C. Using date functions without conversion risks errors if the dates are in text format and not recognized properly.
- D. Transforming dates to numerical values and using math functions is unreliable and does not account for date-specific logic.
Question 27
Which of the following best describes the method used to combine files, software, and libraries for use on various operating systems and environments?
Show answer and explanation
Correct answer: D. Containerization
Containerization is the method that packages files, software, libraries, and dependencies into isolated containers that can run consistently across various operating systems and environments. Containers abstract the application from the underlying infrastructure, ensuring portability and consistency.
Why the other options are wrong
- A. A package manager handles software installation and dependencies but does not provide cross-environment isolation.
- B. A code repository stores source code but does not provide deployment or execution across different environments.
- C. A virtual machine emulates entire operating systems but is heavier and less efficient than containerization.
Question 28
A teaching administrator wants to measure the distribution of student scores in a class. Which of the following statistical measures should the administrator use?
Show answer and explanation
Correct answer: A. Standard deviation
Standard deviation measures how spread out the student scores are from the mean, directly showing the distribution pattern. While variance (D) also measures dispersion, standard deviation is the more commonly reported measure because it uses the same units as the original data, making it more interpretable for this practical administrative purpose.
Why the other options are wrong
- B. Geometric progression is a mathematical sequence concept, not a statistical measure of distribution.
- C. A t-test is a hypothesis testing method used to compare means between groups, not to measure distribution of scores within a single group.
- D. Variance measures dispersion but is less practical than standard deviation because it's in squared units, making it harder to interpret in context.
Question 29
Which of the following tools would a data analyst most likely use to modify a simple data connection property in a configuration file?
Show answer and explanation
Correct answer: C. Notepad++
Notepad++ is a lightweight text editor designed for editing configuration files and scripts. It is ideal for modifying simple data connection properties in configuration files, offering syntax highlighting and file management capabilities without the overhead of database-specific or statistical tools.
Why the other options are wrong
- A. RStudio is a statistical and data analysis IDE, not a general text editor for configuration files.
- B. SSMS (SQL Server Management Studio) is a database management tool, not designed for editing general configuration files.
- D. Toad is a database development and administration tool, not a general text editor for configuration file modification.
Question 30
A data analyst is evaluating all conditions in a query. Which of the following is the best logical function to accomplish this task?
Show answer and explanation
Correct answer: C. AND
The AND operator evaluates all conditions in a query and returns results only when every condition is true. This is the logical function needed to ensure that all specified conditions are met simultaneously, making it ideal for comprehensive condition evaluation.
Why the other options are wrong
- A. OR returns results when any condition is true, not all conditions.
- B. NOT inverts or negates a condition, not evaluates multiple conditions comprehensively.
- D. IF is a conditional control structure, not a logical operator for evaluating multiple query conditions.
Question 31
The human resources department wants to understand the relationship between the ages and incomes of all employees. Which of the following graphics is the most appropriate to present the analysis?
Show answer and explanation
Correct answer: A. Scatter plot
A scatter plot is the most appropriate graphic for displaying the relationship between two continuous variables, such as age and income. It clearly shows correlation, clustering, and outliers between the two variables on an x-y coordinate system.
Why the other options are wrong
- B. An area plot is used for showing changes over time, not relationships between two variables.
- C. A bar chart compares categorical or discrete values, not the relationship between two continuous variables.
- D. A pie chart shows proportions of a whole and is not appropriate for comparing two independent variables.
Question 32
A data analyst is helping a company achieve its strategic goals. Which of the following types of analytics should the analyst incorporate into the dashboards and tools delivered to the company?
Show answer and explanation
Correct answer: A. Prescriptive
Prescriptive analytics is the most comprehensive type that should be incorporated into dashboards and tools to help achieve strategic goals. It goes beyond describing what happened (descriptive), explaining why it happened (diagnostic), or predicting what will happen (predictive) by actually recommending specific actions to take. This is most aligned with helping a company achieve its strategic objectives.
Why the other options are wrong
- B. Predictive analytics forecasts future outcomes but does not recommend actions to achieve strategic goals.
- C. Diagnostic analytics explains why something happened but does not guide future strategy.
- D. Descriptive analytics only summarizes historical data and does not support strategic decision-making.
Question 33
While interacting with a data set. a data analyst learns that copies of the data are distributed across several data repositories around the globe. Which of the following concepts best describes this practice?
Show answer and explanation
Correct answer: C. Replication
Replication describes the practice of maintaining copies of data across multiple geographic locations or repositories. This ensures availability and fault tolerance by distributing identical copies of the data.
Why the other options are wrong
- A. Redundancy is a broader concept referring to backup copies, not the specific practice of distributed global copies.
- B. High availability is an outcome or goal, not the technical practice of distributing data copies.
- D. Duplication is a generic term; replication is the more precise technical term for this distributed data practice.
Question 34
Which of the following data sources makes online data consumption easier?
Show answer and explanation
Correct answer: D. Application programming interface
An application programming interface (API) is designed specifically to make online data consumption easier by providing a standardized, programmatic way to access data. APIs handle authentication, rate limiting, data formatting, and integration, allowing analysts to easily retrieve data from online sources in a reliable, documented manner. This is the primary purpose of APIs in modern data workflows.
Why the other options are wrong
- A. A data mart is an internal repository focused on specific business areas and is not designed for easier online data consumption.
- B. Web scraping is a more labor-intensive, fragile method that requires custom code and is vulnerable to website structure changes.
- C. A database is a general storage system designed for internal data management, not specifically for facilitating online data consumption.
Question 35
A data analyst is creating a dashboard for a group of visually impaired stakeholders. Which of the following communication approaches is best?
Show answer and explanation
Correct answer: C. Incorporate audio accessibility functions into graphics for all instances of the interface.
Incorporating audio accessibility functions directly into the graphics ensures visually impaired stakeholders can independently access the dashboard content. This is the most direct and inclusive solution that provides equal access to all interface elements.
Why the other options are wrong
- A. Informing the supervisor shifts responsibility rather than solving the accessibility problem directly.
- B. Working with HR addresses advocacy but does not actually make the dashboard accessible.
- D. Interactive sound effects are not a substitute for proper accessibility functions and may be distracting rather than informative.
Question 36
A data analyst receives a request for the current employee head count and runs the following SQL statement: • SELECT COUNT(EMPLOYEE_ID) • FROM JOBS The returned head count is higher than expected because employees can have multiple jobs. Which of the following should return an accurate employee head count?
Show answer and explanation
Correct answer: D. SELECT COUNT(DISTINCT EMPLOYEE_ID) FROM JOBS
To return an accurate count of unique employees regardless of how many jobs each has, COUNT(DISTINCT EMPLOYEE_ID) counts each employee only once. This directly addresses the problem where the original query counted employees multiple times because they appear multiple times in the JOBS table due to multiple job assignments.
Why the other options are wrong
- A. Missing the COUNT function and incorrect syntax; DISTINCT without COUNT would not return a numeric count.
- B. DISTINCT at the query level doesn't work with COUNT in this way; the syntax is incorrect and wouldn't aggregate properly.
- C. Including JOB_TYPE in the SELECT without aggregation creates a grouped result set rather than a single head count value.
Question 37
A data analyst is creating a statistical table that contains basic information about the data set. Which of the following is the best statistical method for this scenario?
Show answer and explanation
Correct answer: A. Descriptive
Descriptive statistics is the appropriate method for creating a statistical table with basic information about a dataset. Descriptive statistics summarize and describe the main characteristics of data, such as mean, median, standard deviation, counts, and distributions. This method is used when the goal is to understand and present the current state of data, which is exactly what a statistical table with basic information accomplishes.
Why the other options are wrong
- B. Predictive statistics is used to forecast future outcomes based on historical data, not to describe current data.
- C. Inferential statistics draws conclusions about populations from samples, not simply to describe basic data characteristics.
- D. Prescriptive statistics recommends actions based on analysis, which is beyond the scope of creating a basic informational table.
That was 37 of 148.
The full CompTIA Data+ DA0-002 pack has all 148 questions, each with the answer, the explanation and why the other options are wrong, plus a questions-only copy for timed runs. US$39, paid once, with free monthly updates and a pass-or-your-money-back guarantee.
Not ready yet? Get the first 74 free as one PDF by email. Get the Half Pack →