DA0-002 Practice Test 20 — 15 Questions

Question 1

A logistic regression model is used to predict the probability of customer churn. The model's coefficient for the feature 'customer support calls' is 0.8 with a p-value of 0.001. Which interpretation is correct?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

For each additional support call, the log-odds of churn increase by 0.8, and this effect is statistically significant.. In logistic regression, coefficients are expressed in log-odds units. A coefficient of 0.8 for 'customer support calls' means each additional call increases the log-odds of churn by 0.8, holding other predictors constant. The p-value of 0.001 is below the conventional 0.05 threshold, so the effect is statistically significant.

Answer

The odds of churn are multiplied by 0.8 for each additional call.

Answer

Support calls have no significant effect on churn.

Answer

For each additional support call, the probability of churn increases by 80%.

Question 2

A data architect is designing a system to store data for a real-time analytics application. The application requires high-speed ingestion of semi-structured data with flexible schemas, and the ability to query data using SQL-like syntax. The data volume is expected to grow rapidly. Which type of database should the architect choose?

Accepted Answer

NoSQL document database. A NoSQL document database is the best choice because it handles semi-structured data with flexible schemas, supports high-speed ingestion, and scales horizontally. It often provides SQL-like query capabilities. Relational databases are too rigid, data warehouses are for structured historical data, and graph databases are for relationship-heavy use cases.

Answer

Graph database

Answer

Relational database

Answer

Data warehouse

Question 3

A logistics company uses a key-value store to cache real-time shipment tracking updates. The data model has no fixed schema, and each shipment record may contain different attributes. Which data storage approach is being used?

Accepted Answer

NoSQL key-value store. The scenario describes storing shipment records under unique identifiers with varying attributes and no fixed schema, which is the defining characteristic of a key-value store. Key-value stores excel at fast, simple lookups by key, making them ideal for caching real-time tracking updates. Relational databases, warehouses, and lakes impose structure or latency that conflict with these requirements.

Answer

Relational database

Answer

Data warehouse

Answer

Data lake

Question 4

Which data cleaning method involves replacing a missing value with the average of the available values in that column?

Accepted Answer

Mean imputation. Mean imputation is the data cleaning technique that replaces missing values in a column with the arithmetic mean (average) of the non-missing values in that same column. This preserves the column's central tendency and keeps the overall sample size intact, which is why it is the standard answer when the question specifies 'replacing a missing value with the average of the available values in that column.'

Answer

Interpolation

Answer

Listwise deletion

Answer

Forward-fill

Question 5

A healthcare analytics team stores patient visit records in a relational database. Each visit has a unique VisitID, and the team frequently needs to join visit data with physician and facility tables. The database must enforce referential integrity between these tables. Which data model characteristic best describes this environment?

Accepted Answer

A normalized relational model with primary and foreign key constraints. The described environment requires unique identifiers, joins across multiple related tables, and enforced referential integrity. These are defining characteristics of a normalized relational model using primary and foreign keys. Alternative models either lack join capabilities or do not enforce integrity constraints, making them unsuitable for this healthcare analytics scenario.

Answer

A document-oriented NoSQL store with embedded visit documents

Answer

A key-value store using VisitID as the lookup key

Answer

A denormalized star schema optimized for analytical query speed

Question 6

A data analyst is profiling a dataset of employee records. The birthdate column contains values stored as text in the format YYYY-MM-DD, while the hire date column is stored as a native date type. The analyst needs to calculate employee tenure. Which action should the analyst take first?

Accepted Answer

Calculate the difference between the hire date and the current date. Tenure is the elapsed time between an employee's hire date and the present. Because the hire date is already stored as a native date type, the analyst can compute the difference directly without any conversion. The birthdate column's text format is a separate data quality issue that does not affect the tenure calculation and should not block it.

Answer

Convert the hire date column from native date to text to match the birthdate column

Answer

Subtract the birthdate from the hire date to derive tenure

Answer

Convert the birthdate column from text to a native date type

Question 7

A marketing analyst receives a dataset containing customer ages recorded as whole numbers (for example, 25, 42, 67). The analyst wants to classify the measurement scale of the age field. Which measurement scale applies?

Accepted Answer

Ratio. Age in years possesses a true zero, equal intervals between consecutive values, and supports meaningful arithmetic and ratios. These are the defining properties of the ratio scale. Nominal and ordinal scales lack the numeric structure required, while interval scales lack a true zero, so ratio is the appropriate classification.

Answer

Ordinal

Answer

Interval

Answer

Nominal

Question 8

A financial analyst is creating a quarterly report compliant with SOX. Which requirement is most critical for the report's audit trail?

Accepted Answer

Audit trail of data changes. SOX compliance requires that financial reports be traceable and that any change to reported data be attributable to a specific user at a specific time. An audit trail of data changes (B) provides exactly this: a tamper-evident record of who changed what, when, and why, which is the core control auditors test for financial reporting integrity. Without it, the report cannot be defended as accurate or complete during an audit.

Answer

Row-level security

Answer

Data lineage

Answer

Data dictionary

Question 9

A data analyst is working with a dataset that includes a column 'Annual Income' with values ranging from $20,000 to $500,000. The analyst wants to reduce the impact of extreme values on a machine learning model. Which technique should the analyst apply?

Accepted Answer

Winsorizing. The correct answer is Winsorizing because it directly caps extreme values at a chosen percentile, reducing their influence on the model. Min-max normalization and z-score standardization do not mitigate outliers, and log transformation only reduces skewness without bounding values.

Answer

Log transformation

Answer

Z-score standardization

Answer

Min-max normalization

Question 10

A data analyst is creating a data story for a marketing campaign results. Which of the following narrative structures is most effective for engaging the audience?

Accepted Answer

Start with a key insight or finding, then provide supporting evidence.. Starting with a key insight or finding and then providing supporting evidence follows the inverted pyramid structure, which is the most effective narrative for engaging an audience. It immediately captures attention with the 'so what' and then justifies it with data. This approach aligns with best practices in data storytelling, where the headline finding drives interest before details are presented.

Answer

Use a question-and-answer format without a clear flow.

Answer

Present all data points chronologically.

Answer

Start with the methodology, then data, then results.

Question 11

A company wants to segment its customers into distinct groups based on purchasing behavior. Which algorithm is best suited for this task?

Accepted Answer

K-means clustering. K-means clustering is an unsupervised learning algorithm that partitions data into K distinct clusters based on feature similarity, making it ideal for segmenting customers by purchasing behavior without predefined labels. It groups customers who exhibit similar purchasing patterns, enabling the company to identify natural segments for targeted marketing.

Answer

Decision tree

Answer

Logistic regression

Answer

Linear regression

Question 12

A data analyst is analyzing survey responses where respondents rated satisfaction on a scale of 1-5. The analyst wants to visualize the distribution of responses. Which chart type is most appropriate?

Accepted Answer

Histogram. A histogram is the most appropriate chart for visualizing the distribution of a single discrete variable, such as satisfaction ratings on a 1-5 scale. It groups the responses into bins (each rating value) and displays the frequency of each bin using bars, clearly showing the shape, central tendency, and spread of the data.

Answer

Box plot

Answer

Scatter plot

Answer

Line chart

Question 13

A data engineer loads a CSV export into a table. The source system writes the value '007' for a product code, but after loading, an analyst queries the table and sees the value 7. The analyst needs the leading zero preserved for downstream matching against another system. Which action should the engineer take?

Accepted Answer

Store the product code in a character or string column so the leading zero is retained. Product codes are identifiers, not quantities, so leading zeros are meaningful and must be preserved. Storing the value in a character column keeps '007' intact and allows reliable matching with other systems, whereas numeric storage strips the zero and presentation formats do not survive joins or exports.

Answer

Create a derived column that concatenates a literal zero with the numeric product code

Answer

Change the column data type to a numeric type with a display format that pads to three digits

Answer

Add a check constraint that rejects any product code shorter than three characters

Question 14

A data analyst is evaluating a binary classification model for loan default prediction. The model achieves 98% accuracy on the test set, but the analyst notices that only 2% of loans in the dataset actually defaulted. The analyst is concerned that accuracy is misleading. Which metric should the analyst examine to better assess the model's ability to identify actual defaulters?

Accepted Answer

Recall. In imbalanced classification, accuracy can be misleading because a model that always predicts the majority class achieves high accuracy but fails to identify the minority class. Recall focuses on the minority class by measuring how many actual positives were correctly identified. For loan default prediction, missing a defaulter is costly, so recall is a key metric. The other metrics are for regression or model fit, not classification performance.

Answer

Mean Absolute Error (MAE)

Answer

Adjusted R-squared

Answer

Root Mean Squared Error (RMSE)

Question 15

A data engineer is designing storage for a fraud detection system that ingests millions of transaction events per second. The system must store each event with its timestamp and support fast writes without predefined schema enforcement, while allowing later analytical queries over semi-structured payloads. Which storage approach best fits these requirements?

Accepted Answer

A document-oriented NoSQL database with schema-on-read. The requirements combine high-velocity ingestion, absence of predefined schema, and support for semi-structured payloads with later analytical querying. Document-oriented NoSQL databases provide schema-on-read flexibility and horizontal write scalability that match these needs. Relational, columnar, and graph systems each impose constraints or optimizations that conflict with one or more of the stated requirements.

Answer

A relational OLTP database with third normal form tables

Answer

A graph database optimized for relationship traversal

Answer

A columnar data warehouse with strict schema-on-write