BrainStation AI Data Analyst Certification (DAC™) — Questions and Answers

Question 1: Which probability distribution is symmetric and bell-shaped, often used as a basis for statistical inference?

Exponential distribution
Binomial distribution
Normal distribution (Correct answer)
Poisson distribution

Correct answer: Normal distribution

The normal distribution is a symmetric, bell-shaped continuous probability distribution fundamental to many statistical methods and the Central Limit Theorem.

Question 2: Which of the following best describes structured data?

Data stored only in cloud systems.
Data exclusively generated from sensors.
Data that lacks a defined format.
Data organized in rows and columns. (Correct answer)

Correct answer: Data organized in rows and columns.

Structured data refers to information that is highly organized and follows a predefined format, making it easily searchable and analyzable. It typically resides in relational databases or spreadsheets, where data elements are arranged in tables with rows and columns, each having a specific type and meaning, ensuring consistency and clarity.

Question 3: Which of the following is an example of prescriptive analytics?

A forecast predicting next month's customer churn rate
A dashboard displaying current website traffic
A report showing last quarter's sales by region
An optimization model recommending the best pricing strategy to maximize revenue (Correct answer)

Correct answer: An optimization model recommending the best pricing strategy to maximize revenue

Prescriptive analytics goes beyond prediction to recommend specific actions, often using optimization algorithms to identify the best course of action.

Question 4: What is a common advantage of separating storage from compute in cloud analytics architectures?

Queries always run on a single node
Each can scale independently to control cost (Correct answer)
Data can never be deleted
It eliminates the need for security

Correct answer: Each can scale independently to control cost

Decoupling storage and compute lets each scale independently, optimizing performance and cost.

Question 5: What is self-service BI?

A BI system that requires no human oversight
An approach allowing business users to access, analyze, and visualize data without relying on IT or data teams (Correct answer)
Automated report delivery via email
A single-user license for BI software

Correct answer: An approach allowing business users to access, analyze, and visualize data without relying on IT or data teams

Self-service BI empowers non-technical business users to independently explore data, create reports, and derive insights using intuitive tools without IT dependency.

Question 6: Prescriptive analytics is best described as:

Explaining past events
Counting records
Cleaning data
Recommending actions to achieve an outcome (Correct answer)

Correct answer: Recommending actions to achieve an outcome

Prescriptive analytics suggests actions to optimize a desired outcome.

Question 7: Which of the following best describes a heat map?

A pie chart split by percentage
A line chart of temperature over time
A geographic map with pins
A chart showing values as color intensity across a matrix (Correct answer)

Correct answer: A chart showing values as color intensity across a matrix

A heat map encodes values as color intensity across a grid or matrix.

Question 8: What does the Central Limit Theorem state?

As sample size increases, the sampling distribution of the mean approaches a normal distribution (Correct answer)
All datasets are normally distributed
Larger samples always produce smaller standard deviations
The sample mean will equal the population mean exactly

Correct answer: As sample size increases, the sampling distribution of the mean approaches a normal distribution

The Central Limit Theorem states that with a sufficiently large sample size, the distribution of sample means will approximate a normal distribution regardless of the population's shape.

Question 9: What does a regression coefficient (slope) represent in a simple linear regression model?

The correlation between the two variables
The percentage of variance explained by the model
The expected change in the dependent variable for a one-unit increase in the independent variable (Correct answer)
The value of the dependent variable when the independent variable is zero

Correct answer: The expected change in the dependent variable for a one-unit increase in the independent variable

The regression slope coefficient quantifies how much the predicted outcome changes for each one-unit increase in the predictor variable, holding other factors constant.

Question 10: In SQL, what does the DISTINCT keyword do?

Filters rows based on a condition
Sorts results in ascending order
Joins two tables together
Removes duplicate values from the result set (Correct answer)

Correct answer: Removes duplicate values from the result set

DISTINCT eliminates duplicate rows from a query result, returning only unique values for the selected columns.

Question 11: Which of the following is an unsupervised learning task?

Grouping customers into segments without labels (Correct answer)
Predicting house prices from features
Classifying emails as spam or not spam
Forecasting next month's sales

Correct answer: Grouping customers into segments without labels

Clustering customers without predefined labels is a classic unsupervised learning task.

Question 12: When designing for mobile dashboards, which approach is recommended?

Show all desktop charts at once
Disable all interactivity
Use very small unlabeled charts
Prioritize key metrics and use a responsive vertical layout (Correct answer)

Correct answer: Prioritize key metrics and use a responsive vertical layout

Mobile dashboards should prioritize key metrics in a responsive, scrollable vertical layout.

Question 13: What is the purpose of a data mart in a BI architecture?

To store raw unprocessed data before ETL
To replace the data warehouse for smaller organizations
To serve as a real-time operational database
To provide a department-specific subset of a data warehouse focused on a particular subject area (Correct answer)

Correct answer: To provide a department-specific subset of a data warehouse focused on a particular subject area

A data mart is a focused subset of a data warehouse designed to serve the analytical needs of a specific business department or subject area (e.g., sales, finance).

Question 14: Grouping continuous ages into ranges like 0-18, 19-35, 36-60 is an example of what?

Joining
Deduplication
Binning (Correct answer)
Imputation

Correct answer: Binning

Binning buckets continuous values into discrete interval categories.

Question 15: A stacked bar chart is best used to show what?

Composition of a total across categories (Correct answer)
Correlation between variables
Exact geographic distance
Precise part-to-whole comparisons across many segments

Correct answer: Composition of a total across categories

Stacked bars show how a total is composed of subcategories across categories.

Question 16: A stakeholder needs to understand exactly why a model made each prediction. Which model type is most interpretable?

Random forest with 500 trees
Logistic regression (Correct answer)
Gradient boosting ensemble
Deep neural network

Correct answer: Logistic regression

Logistic regression offers transparent, coefficient-based explanations that are easy to interpret.

Question 17: A regression model has a high R-squared but residuals show a clear curved pattern. What does this indicate?

A nonlinear relationship is not being captured (Correct answer)
The model is perfect
The data has no relationship
Multicollinearity is present

Correct answer: A nonlinear relationship is not being captured

Systematic curvature in residuals signals that a linear model is missing a nonlinear relationship.

Question 18: In data analytics, what is the interquartile range (IQR) used for?

Calculating the correlation between variables
Determining the statistical significance of results
Identifying the middle 50% of data and detecting outliers (Correct answer)
Measuring the average of a dataset

Correct answer: Identifying the middle 50% of data and detecting outliers

The IQR is the difference between the 75th and 25th percentiles, representing the spread of the middle 50% of data and commonly used in outlier detection.

Question 19: What is a p-value in statistical hypothesis testing?

The power of a statistical test
The probability of obtaining results at least as extreme as observed, assuming the null hypothesis is true (Correct answer)
The percentage of data that is correct
The precision of a measurement

Correct answer: The probability of obtaining results at least as extreme as observed, assuming the null hypothesis is true

A p-value represents the probability of observing results as extreme as or more extreme than the data, given that the null hypothesis is true. A p-value below a chosen threshold (typically 0.05) leads to rejecting the null hypothesis.

Question 20: Which principle suggests placing the most important dashboard metric in the top-left area?

Golden ratio only
Random placement
Center-only focus
Z-pattern / F-pattern reading flow (Correct answer)

Correct answer: Z-pattern / F-pattern reading flow

Western readers scan in Z/F patterns, so key metrics belong top-left.

Question 21: Which of the following best describes a data lake?

A cache layer for frequently accessed reports
A repository that stores vast amounts of raw data in its native format until needed (Correct answer)
A structured relational database for OLTP workloads
A visualization layer on top of a data warehouse

Correct answer: A repository that stores vast amounts of raw data in its native format until needed

A data lake stores large volumes of raw, unstructured, semi-structured, and structured data in its native format, offering flexible schema-on-read capabilities.

Question 22: What does ROI stand for, and how is it used in analytics strategy?

Rate of Inflation, used to adjust revenue figures
Return on Investment, used to measure the profitability of analytics initiatives relative to their cost (Correct answer)
Reporting of Indicators, used in dashboard design
Range of Insight, used to describe the breadth of data analyzed

Correct answer: Return on Investment, used to measure the profitability of analytics initiatives relative to their cost

ROI (Return on Investment) measures the net benefit of an analytics investment relative to its cost, helping justify data projects and prioritize resources.

Question 23: What distinguishes descriptive analytics from predictive analytics?

Descriptive analytics summarizes historical data; predictive analytics forecasts future outcomes (Correct answer)
Descriptive analytics is more accurate than predictive analytics
Descriptive analytics uses machine learning; predictive analytics uses SQL
Predictive analytics only works with structured data

Correct answer: Descriptive analytics summarizes historical data; predictive analytics forecasts future outcomes

Descriptive analytics answers 'what happened?' by summarizing past data, while predictive analytics answers 'what will happen?' using statistical models and historical patterns.

Question 24: What does standard deviation measure in a dataset?

The average distance of data points from the mean (Correct answer)
The correlation between two variables
The most common value in the data
The total range of values

Correct answer: The average distance of data points from the mean

Standard deviation quantifies how spread out the data values are around the mean — a larger value indicates more variability.

Question 25: In regression analysis, what does the R-squared value represent?

The significance of individual predictors
The slope of the regression line
The proportion of variance in the dependent variable explained by the independent variables (Correct answer)
The number of variables in the model

Correct answer: The proportion of variance in the dependent variable explained by the independent variables

R-squared (coefficient of determination) measures the proportion of variance in the outcome variable that is explained by the predictor variables in the model.

Question 26: What is the purpose of ANOVA (Analysis of Variance)?

To compare the means of three or more groups simultaneously (Correct answer)
To measure the correlation between two variables
To calculate the standard deviation of a sample
To test the normality of a dataset

Correct answer: To compare the means of three or more groups simultaneously

ANOVA tests whether the means of three or more independent groups are statistically different from each other, using variance within and between groups.

Question 27: Which metric type is best visualized with a gauge or bullet chart?

Progress toward a target or goal (Correct answer)
Correlation between variables
Geographic clustering
Text frequency

Correct answer: Progress toward a target or goal

Gauge and bullet charts show a value relative to a target or threshold.

Question 28: A KPI dashboard should primarily focus on what?

Only raw data tables
A small set of metrics tied to business goals (Correct answer)
Random sample charts
Every available metric

Correct answer: A small set of metrics tied to business goals

Effective dashboards highlight a focused set of key performance indicators aligned to objectives.

Question 29: In data governance, what does 'data lineage' refer to?

The number of rows in a table
The encryption standard applied to data
The tracking of data's origin, movement, and transformations over time (Correct answer)
The age of a dataset

Correct answer: The tracking of data's origin, movement, and transformations over time

Data lineage documents the lifecycle of data — where it originates, how it moves, and how it is transformed — enabling auditability and troubleshooting.

Question 30: Which ethical framework emphasizes that data analytics decisions should maximize overall benefit to society, even if individual rights may be slightly infringed?

Rights-based ethics
Virtue ethics
Deontological ethics
Utilitarianism (Correct answer)

Correct answer: Utilitarianism

Utilitarianism evaluates actions based on their consequences, aiming to produce the greatest good for the greatest number of people.

Question 31: In BI, what does a star schema consist of?

A flat file structure without primary keys
A central fact table surrounded by denormalized dimension tables (Correct answer)
A normalized relational schema with many foreign key joins
Multiple interconnected fact tables with no dimension tables

Correct answer: A central fact table surrounded by denormalized dimension tables

A star schema features a central fact table containing measurable business events connected to denormalized dimension tables that provide descriptive context.

Question 32: Which statistical test is appropriate for comparing the means of two independent groups?

Independent samples t-test (Correct answer)
Pearson correlation
ANOVA
Chi-square test

Correct answer: Independent samples t-test

The independent samples t-test compares the means of two unrelated groups to determine if there is a statistically significant difference.

Question 33: In Excel, which feature creates an interactive summary table that can be quickly re-arranged by dragging fields?

VLOOKUP
Conditional formatting
Data validation
PivotTable (Correct answer)

Correct answer: PivotTable

A PivotTable summarizes and reorganizes data interactively by dragging fields.

Question 34: Which chart type best displays the correlation between two continuous numeric variables?

Word cloud
Scatter plot (Correct answer)
Gauge
Pie chart

Correct answer: Scatter plot

A scatter plot maps two numeric variables on the X and Y axes to reveal correlation.

Question 35: What is a data warehouse in a business intelligence context?

A subject-oriented, integrated repository of historical data optimized for analytical queries (Correct answer)
A physical server room where databases are stored
A tool for creating interactive dashboards
A real-time streaming data pipeline

Correct answer: A subject-oriented, integrated repository of historical data optimized for analytical queries

A data warehouse is a centralized repository of integrated, historical data from multiple sources, designed and optimized for analytical reporting and decision-making.

Question 36: In Google Cloud, which serverless service is designed for running SQL analytics over massive datasets?

Cloud Storage
Compute Engine
BigQuery (Correct answer)
Pub/Sub

Correct answer: BigQuery

BigQuery is Google Cloud's serverless, highly scalable data warehouse for SQL analytics.

Question 37: What does an outlier detected by the IQR method fall outside of?

The median
1.5 times the interquartile range from the quartiles (Correct answer)
The mean plus one standard deviation
The mode

Correct answer: 1.5 times the interquartile range from the quartiles

The IQR rule flags points beyond 1.5×IQR below Q1 or above Q3 as outliers.

Question 38: A report double-counts revenue because the same order appears twice. What cleaning step fixes this?

Imputation
Aggregation
Deduplication (Correct answer)
Normalization

Correct answer: Deduplication

Deduplication removes repeated records so each entity is counted once.

Question 39: What is the primary purpose of data analytics?

To extract insights and support decision-making. (Correct answer)
To encrypt sensitive data for security purposes.
To randomly store large amounts of data.
To replace human decision-making entirely.

Correct answer: To extract insights and support decision-making.

Data analytics is the systematic process of examining raw data to discover meaningful patterns, correlations, and insights. Its primary purpose is to transform data into actionable information, enabling businesses and organizations to make more informed, data-driven decisions and improve various aspects of their operations and strategies.

Question 40: Which visualization is most appropriate for showing geographic sales distribution?

Histogram
Radar chart
Line chart
Choropleth map (Correct answer)

Correct answer: Choropleth map

A choropleth map shades geographic regions by value, ideal for spatial distribution.

Question 41: Which programming language is widely used for data analysis?

HTML
Python (Correct answer)
C++
Swift

Correct answer: Python

Python is widely recognized as a leading programming language for data analysis due to its extensive ecosystem of libraries. Libraries like Pandas, NumPy, SciPy, and Scikit-learn provide powerful tools for data manipulation, statistical analysis, machine learning, and visualization. Its readability and versatility make it a preferred choice for data professionals.

Question 42: A model achieves 99% accuracy on training data but only 62% on test data. What is the most likely problem?

Data leakage from the test set
Class imbalance
Overfitting (Correct answer)
Underfitting

Correct answer: Overfitting

A large gap between high training accuracy and low test accuracy is the classic signature of overfitting.

Question 43: What does a positively skewed distribution indicate about the data?

The data has no outliers
Most values are concentrated on the left side with a long right tail (Correct answer)
Most values are concentrated on the right side with a long left tail
The mean equals the median

Correct answer: Most values are concentrated on the left side with a long right tail

In a positively skewed distribution, the tail extends to the right, meaning most data values are lower but a few extreme high values pull the mean upward.

Question 44: What does the term 'mean' refer to in descriptive statistics?

The most frequently occurring value
The difference between the highest and lowest values
The arithmetic average of all values (Correct answer)
The middle value when data is sorted

Correct answer: The arithmetic average of all values

The mean is calculated by summing all data values and dividing by the count of values, giving the arithmetic average.

Question 45: Which normal form eliminates transitive dependencies in a relational database?

Third Normal Form (3NF) (Correct answer)
First Normal Form (1NF)
Boyce-Codd Normal Form (BCNF)
Second Normal Form (2NF)

Correct answer: Third Normal Form (3NF)

Third Normal Form (3NF) requires that all non-key attributes depend only on the primary key and not on other non-key attributes (no transitive dependencies).

Question 46: Which type of database is best suited for storing and querying highly connected data such as social networks?

Flat file store
Columnar warehouse
Key-value cache
Graph database (Correct answer)

Correct answer: Graph database

Graph databases model entities as nodes and relationships as edges, ideal for connected data.

Question 47: What is a slowly changing dimension (SCD) in data warehousing?

A dimension table that is updated in real time
A type of fact table that updates slowly
A technique for managing and tracking changes to dimension data over time (Correct answer)
A dimension table with fewer than 100 rows

Correct answer: A technique for managing and tracking changes to dimension data over time

Slowly Changing Dimensions (SCDs) are methods (Type 1, 2, 3, etc.) for managing how changes to dimension attributes are tracked and stored in a data warehouse over time.

Question 48: When should you use a bar chart versus a line chart?

They are interchangeable for all data types
Bar charts for comparing categories; line charts for showing trends over time (Correct answer)
Bar charts only for financial data
Line charts only for scientific data

Correct answer: Bar charts for comparing categories; line charts for showing trends over time

Bar charts effectively compare discrete categories or groups, while line charts show continuous data trends over time. Choosing the wrong chart type can misrepresent the data and mislead the audience.

Question 49: Which data quality dimension measures whether data correctly represents real-world values?

Completeness
Timeliness
Uniqueness
Accuracy (Correct answer)

Correct answer: Accuracy

Accuracy refers to how well data values reflect the true real-world state of the entity being described.

Question 50: What is a primary key in a relational database?

A key used for encrypting sensitive data
A foreign key that references another table
The first column in every table by convention
A column or combination of columns that uniquely identifies each row in a table (Correct answer)

Correct answer: A column or combination of columns that uniquely identifies each row in a table

A primary key uniquely identifies each record in a table and cannot contain NULL values, ensuring data integrity.

Question 51: In a balanced scorecard approach to analytics strategy, which of the following is NOT one of the four perspectives?

Customer
Technology Infrastructure (Correct answer)
Financial
Internal Business Processes

Correct answer: Technology Infrastructure

The Balanced Scorecard's four perspectives are Financial, Customer, Internal Business Processes, and Learning & Growth — technology infrastructure is not one of the four.

Question 52: Which type of sampling ensures every member of a population has an equal chance of being selected?

Purposive sampling
Simple random sampling (Correct answer)
Cluster sampling
Convenience sampling

Correct answer: Simple random sampling

Simple random sampling gives every member of the population an equal and independent probability of selection, minimizing selection bias.

Question 53: Which type of analysis uses historical data to forecast future outcomes?

Diagnostic
Exploratory
Predictive (Correct answer)
Descriptive

Correct answer: Predictive

Predictive analysis applies models to historical data to estimate future results.

Question 54: Which approach best prevents data leakage when scaling features?

Scale after model training
Fit the scaler only on training data, then apply to test data (Correct answer)
Never scale features
Fit the scaler on the entire dataset before splitting

Correct answer: Fit the scaler only on training data, then apply to test data

Fitting the scaler only on training data prevents test-set information from leaking into the model.

Question 55: What does 'data validation' primarily ensure?

Data is visually appealing
Data meets defined rules and formats (Correct answer)
Data loads faster
Data is deleted after use

Correct answer: Data meets defined rules and formats

Validation checks that data conforms to expected rules, types, and formats.

Question 56: A dual-axis chart is most useful when you need to:

Display a single metric
Show geographic distribution
Replace a data table
Show two measures with different scales together (Correct answer)

Correct answer: Show two measures with different scales together

Dual-axis charts let you plot two measures with different scales on the same chart for comparison.

Question 57: A stakeholder wants to compare the composition of total sales across five regions over four quarters. Which chart works best?

Single pie chart
Stacked bar chart by quarter (Correct answer)
Scatter plot
Gauge chart

Correct answer: Stacked bar chart by quarter

A stacked bar chart by quarter shows both totals and regional composition over time.

Question 58: Which term describes an outlier in a dataset?

The average value
A value that fits the trend
A missing value
A value that differs markedly from others (Correct answer)

Correct answer: A value that differs markedly from others

An outlier is a data point that deviates significantly from the rest.

Question 59: Which measure of central tendency is most resistant to the influence of extreme outliers?

Mean
Median (Correct answer)
Standard deviation
Variance

Correct answer: Median

The median, being the middle value of a sorted dataset, is not affected by extreme outliers the way the mean is.

Question 60: In statistics, the standard deviation measures:

The middle value
The most frequent value
The spread of data around the mean (Correct answer)
The total count

Correct answer: The spread of data around the mean

Standard deviation quantifies how much values deviate from the mean.

Question 61: Which tool is commonly used for data visualization?

Hadoop
MySQL
Python
Tableau (Correct answer)

Correct answer: Tableau

Tableau is a leading business intelligence and data visualization tool specifically designed for creating interactive and shareable dashboards and reports. It allows users to connect to various data sources and build complex visualizations with a drag-and-drop interface, often without requiring extensive programming knowledge. While Python has visualization libraries, Tableau is a dedicated, user-friendly application.

Question 62: What is a common cause of misleading visualizations even when data is accurate?

Adding chart titles
Using a legend
Inappropriate axis scaling or cherry-picked time ranges (Correct answer)
Using consistent colors

Correct answer: Inappropriate axis scaling or cherry-picked time ranges

Manipulating axis scales or selecting narrow time ranges can distort accurate data.

Question 63: In data governance, what is a 'data dictionary'?

A type of database index
A lookup table for foreign key values
A compression algorithm for large text fields
A document defining the meaning, format, and rules for each data element in a system (Correct answer)

Correct answer: A document defining the meaning, format, and rules for each data element in a system

A data dictionary is a centralized repository that defines all data elements including their names, definitions, data types, and business rules.

Question 64: Which technique is most appropriate for reducing overfitting in a decision tree?

Removing cross-validation
Pruning the tree (Correct answer)
Increasing tree depth
Adding more leaf nodes

Correct answer: Pruning the tree

Pruning removes branches that add little predictive power, reducing complexity and overfitting.

Question 65: In hypothesis testing, what does a p-value less than 0.05 typically indicate?

The sample size is too small
There is statistically significant evidence to reject the null hypothesis (Correct answer)
The data is normally distributed
The null hypothesis is definitely true

Correct answer: There is statistically significant evidence to reject the null hypothesis

A p-value below the significance threshold (commonly 0.05) indicates the observed results are unlikely under the null hypothesis, supporting its rejection.

BrainStation AI Data Analyst Certification (DAC™)

The BrainStation DAC™ certifies proficiency in the full data analytics workflow — including SQL, Excel, Tableau, statistical analysis, data visualization, and business intelligence strategy — for aspiring data analysts.

Questions

90 min

Time Limit

70%

To Pass

Checking for saved progress...

Exam Rules

You can skip questions and return to them later
Flag questions for review before submitting
No feedback shown until you submit the entire exam
Unanswered questions count as wrong — answer everything
10 pretest questions are mixed in and don't affect your score
Timer auto-submits when time runs out
Your progress is auto-saved every 30 seconds