DA0-002 Hard Questions — 25 Difficult Questions

Question 1

Refer to the exhibit. A data architect is designing a data dictionary for a relational database. Based on the exhibit, which data concept is being illustrated?

Accepted Answer

Data constraints. The exhibit shows a table definition with column attributes such as NOT NULL, UNIQUE, and PRIMARY KEY, which are data constraints that enforce rules on the data values. Data constraints ensure data integrity by restricting what data can be stored in a column, such as preventing null values or duplicate entries. This directly aligns with the concept of data constraints, making option A correct.

Answer

Data aggregation

Answer

Data normalization

Answer

Data cardinality

Question 2

A data engineer is designing a system to store raw sensor data from thousands of IoT devices. The data will be used later for various analytics projects, but the schema is not yet defined. Which storage solution is most appropriate?

Accepted Answer

Data lake. A data lake stores raw data in its native format (e.g., S3, ADLS) without requiring a predefined schema, making it suitable for IoT data.

Answer

Data mart

Answer

Data warehouse

Answer

Relational database

Question 3

A data analyst includes a map showing customer locations by zip code. The map reveals exact addresses for a few customers due to data granularity. This violates which principle?

Accepted Answer

Anonymization. The map reveals exact addresses for a few customers due to the granularity of zip code data. This directly violates the principle of anonymization, which requires that data be processed in such a way that individuals cannot be identified. By exposing precise locations, the data is no longer anonymized, as it allows re-identification of specific individuals.

Answer

Informed consent

Answer

Data minimization

Answer

Data quality

Question 4

A data analyst is using a public API to collect historical weather data. The API has a rate limit of 100 requests per minute, but the analyst needs to retrieve 10,000 records as quickly as possible. What strategy should be used?

Accepted Answer

Paginate with appropriate delays. Paginating with appropriate delays respects the API's rate limit of 100 requests per minute while maximizing throughput. By splitting the 10,000 records into pages (e.g., 100 records per page) and sending requests at a rate just under the limit (e.g., one request every 0.6 seconds), the analyst can retrieve all data in approximately 100 minutes without triggering HTTP 429 rate-limit errors.

Answer

Increase the request rate

Answer

Use multiple API keys

Answer

Download a precompiled dataset

Question 5

An analyst is fitting a polynomial regression model and wants to choose the degree that minimizes overfitting. Which technique should the analyst use?

Accepted Answer

Ridge regression (L2). Ridge regression (L2) adds a penalty proportional to the square of the magnitude of coefficients, which shrinks them toward zero but does not eliminate them. This regularization reduces variance and helps prevent overfitting in polynomial regression by controlling the influence of higher-degree terms, making it the correct technique for minimizing overfitting while retaining all features.

Answer

Lasso regression (L1)

Answer

Principal component analysis (PCA)

Answer

Stepwise selection

Question 6

In Tableau, you want to create a view showing the total sales per region, but also want to allow users to filter by year without losing the ability to see all regions. What feature should you use to compute the total sales that ignores the year filter?

Accepted Answer

LOD expression: { FIXED [Region] : SUM([Sales]) }. A Level of Detail (LOD) expression with FIXED can compute a value at the region level, ignoring other dimensions like year.

Answer

Table calculation running total

Answer

Parameter action

Answer

Calculated field using SUM([Sales])

Question 7

A company is merging two databases from different departments. In Database A, customer IDs are integers. In Database B, customer IDs are alphanumeric strings. To merge, the data analyst must reconcile these differences. Which step should be taken first?

Accepted Answer

Perform data profiling to understand the ID formats and relationships. Data profiling is the essential first step before any transformation or mapping. It allows the analyst to examine the actual formats, patterns, and relationships in both ID columns (e.g., whether Database B's alphanumeric IDs contain embedded numeric sequences or consistent prefixes). Without profiling, any conversion or mapping would be based on assumptions that could lead to data loss or incorrect merges.

Answer

Drop the ID column and use a surrogate key

Answer

Convert all IDs to integers using CAST

Answer

Create a mapping table based on the first character

Question 8

Given the linear regression output, which independent variable has the strongest effect on price, based on standardized coefficients?

Accepted Answer

sqft_living. Standardized coefficients (beta weights) allow comparison of the relative strength of independent variables by measuring the number of standard deviations the dependent variable changes per one standard deviation change in the predictor. In the regression output, sqft_living has the highest absolute standardized coefficient, indicating it has the strongest effect on price. The intercept is not an independent variable and its coefficient is not standardized for comparison.

Answer

bathrooms

Answer

Intercept

Answer

bedrooms

Question 9

Which THREE are best practices for acquiring data via web scraping? (Select exactly 3)

Accepted Answer

Respect robots.txt. Options B, C, and E are correct because best practices for web scraping include respecting robots.txt (ethical and legal compliance), identifying yourself with a user-agent (transparency), and limiting request rate (avoid overloading servers). Option A is incorrect because using multiple IP addresses is often used to circumvent blocking, which can violate terms of service and is not a recommended best practice. Option D is incorrect because scraping all data without regard to terms is unethical and potentially illegal.

Answer

Use multiple IP addresses

Answer

Scrape all data without regard to terms

Question 10

Which THREE of the following are assumptions of linear regression? (Select THREE).

Accepted Answer

Independence of errors. Independence of errors is a core assumption of linear regression, meaning the residuals (errors) should not be correlated with each other. This is critical for valid inference because correlated errors violate the Gauss-Markov theorem, leading to biased standard errors and unreliable hypothesis tests. In time series data, this assumption is often violated due to autocorrelation, which can be detected using the Durbin-Watson test.

Answer

Normal distribution of independent variables

Answer

Multicollinearity among independent variables

Question 11

A data analyst is creating a self-service reporting environment. Which data governance practice ensures users see only data relevant to their department?

Accepted Answer

Row-level security. Row-level security restricts data access based on user roles, ensuring users only see authorized data.

Answer

Data lineage

Answer

Data dictionary

Answer

Single version of truth

Question 12

An analyst notices that a dashboard displays conflicting data from two sources. What is the first step in troubleshooting?

Accepted Answer

Check data transformation steps and join logic. The first step in troubleshooting conflicting data from multiple sources is to verify the data transformation steps and join logic. Conflicts often arise from incorrect joins (e.g., using INNER JOIN instead of LEFT JOIN), mismatched keys, or data type conversions that alter values. Checking these steps isolates the root cause before any other action, such as re-running queries or notifying stakeholders.

Answer

Re-run all queries

Answer

Notify stakeholders of potential error

Answer

Replace the data source with the one believed to be correct

Question 13

Based on the exhibit, what is the most likely cause of the import failure?

Accepted Answer

A data quality issue: the date field contains an invalid date.. The exhibit shows a date field containing '2023-02-30', which is an invalid date (February never has 30 days). This data quality issue causes the import to fail, as the system likely validates date values against calendar rules before inserting them into the target table. The error is not due to file emptiness, non-numeric characters, or corruption, but specifically a semantic data integrity violation.

Answer

The file is empty or contains only headers.

Answer

The price field includes non-numeric characters that cannot be parsed.

Answer

The source file is corrupted or in an unsupported format.

Question 14

A healthcare data analyst is presenting findings on patient readmission rates to a group of hospital administrators. The analysis reveals a 15% increase in readmissions over the past quarter for patients aged 65+ from a specific zip code. However, the administrators are skeptical because previous quarterly reports showed no such trend, and they suspect data quality issues. The analyst must communicate this insight effectively while maintaining credibility. Which of the following approaches should the analyst take?

Accepted Answer

Acknowledge the discrepancy and explain possible reasons such as changes in data collection methods or patient population. It demonstrates the core competency of 'Communicating Data Insights' by acknowledging the discrepancy between the current finding and previous reports, which builds trust with skeptical stakeholders. By explaining possible reasons such as changes in data collection methods or patient population, the analyst maintains credibility and invites collaborative investigation into data quality issues, rather than dismissing concerns or hiding details.

Answer

Emphasize the statistical significance of the finding and ignore previous reports

Answer

Present the data without any explanation and let them draw conclusions

Answer

Remove the demographic detail to avoid controversy

Question 15

A data analyst is performing a chi-square test of independence on a contingency table of customer satisfaction (satisfied vs. dissatisfied) and product type (A, B, C). The test yields a p-value of 0.04 with α = 0.05. What is the correct conclusion?

Accepted Answer

There is a significant association between satisfaction and product type.. Since p-value < α, we reject the null hypothesis of independence, meaning there is a significant association between satisfaction and product type.

Answer

There is no evidence of an association between satisfaction and product type.

Answer

The test is invalid because the expected counts are too low.

Answer

Satisfaction and product type are independent.

Question 16

A data analyst runs an A/B test on a new website layout. The test yields a p-value of 0.04 with the null hypothesis being no difference in conversion rates. The significance threshold is α=0.05. Which of the following is the correct conclusion?

Accepted Answer

Reject the null hypothesis; there is a statistically significant difference in conversion rates.. Since p-value (0.04) < α (0.05), we reject the null hypothesis and conclude there is a statistically significant difference. However, statistical significance does not guarantee practical significance.

Answer

The result is not significant; accept the alternative hypothesis.

Answer

Reject the null hypothesis; the new layout is proven to increase conversions.

Answer

Fail to reject the null hypothesis; there is no evidence of a difference.

Question 17

A company runs an A/B test to compare a new website layout (treatment) against the current layout (control). The conversion rate for the control is 5% and for the treatment is 5.5%. The p-value is 0.06 at α=0.05. Which THREE of the following conclusions are valid?

Accepted Answer

There is not enough evidence to conclude that the new layout is better.. The p-value > α, so fail to reject the null; the difference is not statistically significant. However, the observed lift is 0.5% (absolute). Sample size might be insufficient; statistical power could be low.

Answer

The test has sufficient power to detect the observed effect.

Answer

The new layout significantly increases conversion rate.

Question 18

A research firm is acquiring data from public government databases via API. The API rate limits at 100 requests per minute. They need to download 10,000 records, but each request returns a maximum of 100 records. What is the most efficient approach to ensure complete acquisition without being blocked?

Accepted Answer

Use a retry logic with exponential backoff and pagination. Pagination with retry logic using exponential backoff allows the firm to send requests in a controlled manner, respecting the rate limit and handling potential failures. Sending all requests in parallel would likely exceed the rate limit and cause blocking. Downloading one record per second is too slow. Requesting a data dump via email is inefficient and may not be supported.

Answer

Request a data dump from the government via email

Answer

Download one record per second

Answer

Send all requests simultaneously in parallel

Question 19

An e-commerce company wants to analyze sales performance across product categories. The dataset includes transaction amounts and a column 'category' with values (Electronics, Clothing, Home). The analyst decides to use stratified sampling to ensure proportional representation. Which THREE steps are required to implement this? (Select THREE).

Accepted Answer

Calculate the proportion of each category in the population. Stratified sampling requires dividing the population into strata (categories), then randomly sampling from each stratum in proportion to its size. Combining strata or simple random sampling without stratification would not achieve proportional representation.

Answer

Select every 10th transaction from the entire dataset

Answer

Combine all categories into a single group and perform simple random sampling

Question 20

A healthcare organization is building a data warehouse to support population health analytics. The data sources include: (1) an electronic health record (EHR) system with a relational database containing patient demographics, diagnoses, and medications; (2) a claims system that generates CSV files daily; (3) patient-generated health data from mobile apps via a REST API returning JSON. The data engineer needs to design a data acquisition process that runs nightly. The EHR system has a change tracking mechanism that logs changes with timestamps. The claims CSV files are appended daily. The API supports filtering by date. The data warehouse uses a star schema with fact and dimension tables. The engineer must ensure data consistency and minimize load times. Which approach should the engineer take?

Accepted Answer

Extract only new and changed EHR data using change tracking, extract the full claims CSV (since it's append-only), and extract API data filtered by the last extraction date. It uses incremental extraction for the EHR system (via change tracking) and the API (via date filtering), while performing a full extraction of the claims CSV since it is append-only and small enough to reload nightly. This minimizes load times by avoiding full re-extraction of large, slowly changing datasets, and ensures data consistency by capturing only new or modified records. The star schema in the data warehouse is then populated efficiently from these targeted extracts.

Answer

Perform a full extraction of all data from all sources every night and load directly into the data warehouse

Answer

Use a staging area to land all raw data first, then transform and load

Answer

Extract the EHR data using change tracking, extract the full claims CSV, and extract the API data using a full dump