Data Plus Exam Prep Free practice test →

Free Data Plus Practice Questions

10 free, exam-style Data Plus (Data Plus) practice questions with answers and explanations. No signup required. Work through them below, then take the full free Data Plus practice test to study every exam domain.

These 10 free Data Plus questions are organized by exam domain, so you can see how each part of the Data Plus blueprint is tested. Reveal the answer and explanation under each question.

Domain 1: Data Concepts and Environments 20% of exam

Question 1

A retail company needs to track both current and historical customer addresses so that past orders can always be linked to the address at the time of purchase. Which slowly changing dimension (SCD) type BEST meets this requirement?

  1. Type 1 - overwrite the old address with the new one
  2. Type 2 - add a new row with effective start and end dates
  3. Type 3 - add a column to store the previous address
  4. Type 0 - retain the original address and never update it
Show answer & explanation

Correct answer: B - Type 2 - add a new row with effective start and end dates

Question 2

An international e-commerce company needs to store product descriptions that include Chinese, Arabic, and English characters in the same database column. Which data type is MOST appropriate?

  1. varchar - variable-length character strings
  2. char - fixed-length character strings
  3. nvarchar - variable-length Unicode strings
  4. text - large character objects for long content
Show answer & explanation

Correct answer: C - nvarchar - variable-length Unicode strings

Domain 2: Data Acquisition and Preparation 22% of exam

Question 3

An analyst writes a query that groups orders by customer and needs to return only customers who have placed more than five orders. Which SQL approach is correct?

  1. Add WHERE COUNT(order_id) > 5 before the GROUP BY clause
  2. Add WHERE order_count > 5 after the GROUP BY clause
  3. Add HAVING COUNT(order_id) > 5 after the GROUP BY clause
  4. Add a subquery in the SELECT statement to filter the count
Show answer & explanation

Correct answer: C - Add HAVING COUNT(order_id) > 5 after the GROUP BY clause

Question 4

A data engineer needs to move large volumes of raw, mixed-format data from on-premises systems into a cloud-based data lake for future analysis. Transformations will be applied later as business needs emerge. Which approach is MOST appropriate?

  1. ETL - extract, transform in a staging server, then load to the lake
  2. ELT - extract, load raw data to the lake, then transform in place
  3. Full load with real-time streaming into a normalized data warehouse
  4. Delta load with schema-on-write validation before ingestion
Show answer & explanation

Correct answer: B - ELT - extract, load raw data to the lake, then transform in place

Domain 3: Data Analysis 24% of exam

Question 5

A dataset of home sale prices in a metropolitan area has a mean of $410,000 and a median of $295,000. Which conclusion is BEST supported by these values?

  1. The data is normally distributed with a wide standard deviation
  2. The data contains no outliers because both measures are valid
  3. The distribution is left-skewed with a cluster of low-value properties
  4. The distribution is right-skewed, likely pulled by high-priced properties
Show answer & explanation

Correct answer: D - The distribution is right-skewed, likely pulled by high-priced properties

Question 6

A pharmaceutical company's A/B test on a new drug shows a p-value of 0.02 with a significance level (α) of 0.05. The company concludes the drug is effective and moves to production, but the drug actually has no real effect. Which type of error has occurred?

  1. Type II error - the company failed to detect a true effect
  2. Type I error - the company rejected a true null hypothesis
  3. Sampling error - the sample size was too small to draw conclusions
  4. Measurement error - the data collection instrument was flawed
Show answer & explanation

Correct answer: B - Type I error - the company rejected a true null hypothesis

Question 7

An analyst calculates a correlation coefficient of −0.85 between employee commute distance and job satisfaction score. Which interpretation is MOST accurate?

  1. Longer commutes cause lower job satisfaction in most employees
  2. There is a weak inverse relationship between the two variables
  3. There is a strong negative linear association between the variables
  4. Job satisfaction decreases by 85% for every mile of commute added
Show answer & explanation

Correct answer: C - There is a strong negative linear association between the variables

Domain 4: Visualization and Reporting 20% of exam

Question 8

A marketing team wants to visualize the relationship between monthly advertising spend and the number of new customer sign-ups to determine whether increasing the budget correlates with growth. Which chart type is MOST appropriate?

  1. Line chart with spend on the X-axis and sign-ups over time
  2. Stacked bar chart comparing spend and sign-ups by month
  3. Scatter plot with spend on one axis and sign-ups on the other
  4. Pie chart showing the proportion of budget to sign-ups
Show answer & explanation

Correct answer: C - Scatter plot with spend on one axis and sign-ups on the other

Question 9

A compliance officer needs an identical set of regulatory metrics delivered to leadership on the first business day of every quarter without manual intervention. Which report type is MOST appropriate?

  1. Ad hoc report generated on demand by the compliance team
  2. Dynamic report connected to a live data source with drill-down capability
  3. Self-service report built by leadership using a governed data portal
  4. Recurring scheduled report with automated generation and distribution
Show answer & explanation

Correct answer: D - Recurring scheduled report with automated generation and distribution

Domain 5: Data Governance 14% of exam

Question 10

A hospital needs to share a patient dataset with an external research university. The researchers need realistic data formats to test their analytics pipeline, but no patient should ever be re-identifiable. Which technique BEST meets both requirements?

  1. Anonymization - permanently remove all identifying fields from the dataset
  2. Encryption at rest - store the shared file on an encrypted drive
  3. Role-based access control - restrict the university to read-only permissions
  4. Data masking - replace sensitive values with fictitious data that preserves the original format
Show answer & explanation

Correct answer: D - Data masking - replace sensitive values with fictitious data that preserves the original format

Ready for the real thing?

Practice hundreds more Data Plus questions with instant scoring, weak-area drills, and full exam simulations.

Start the free practice test See pricing