Question 1

Fill in the blank:

Exploratory data analysis is the process of investigating, organizing, and analyzing datasets and _____ their main characteristics.

• summarizing ✅

• modifying ❌

• augmenting ❌

• preparing ❌

Explanation:
EDA emphasizes summarizing data to understand patterns and structure.

---

Question 2

Which EDA process is described?

• Discovering ✅

• Joining ❌

• Validating ❌

• Cleaning ❌

Explanation:
They are learning what the data contains → the Discovering stage.

---

Question 3

Structuring step includes (Select all):

• Organize raw data ✅

• Create data visualizations ❌

• Categorize data into categories representing the dataset ✅

• Transform raw data. ✅

Explanation:
Structuring involves organizing, categorizing, and transforming raw data for usability.

---

Question 4

Correct comparisons of cleaning vs validating (Select all):

• Validating removes errors; cleaning checks validation errors — ❌ (reversed and incorrect)

• When cleaning, look for missing values, duplicates, outliers. When validating, confirm data types. ✅

• Cleaning removes misspellings. Validating does not. ✅

• Cleaning ensures the data is useful. Validating ensures the data is high-quality. ✅

Explanation:
Cleaning fixes problems; validating checks correctness and consistency.

---

Question 5

Add more data when dataset is too small during the _____ process.

• structuring ❌

• cleaning ❌

• joining ✅

• validating ❌

Explanation:
Joining involves combining datasets to expand or enrich the data.

---

Question 6

Best practices for visualizing data during EDA (Select all):

• Ensure visualizations are guided by the data’s story. ✅

• Create ethical, accessible, representative visualizations. ✅

• Design visualizations to support your hypotheses ❌

• Use visualizations throughout EDA to understand the data. ✅

Explanation:
Visualization should be fair, data-driven, and used continuously.

---

Question 7

To avoid miscommunication, data pros can share _____ for early feedback.

• metadata ❌

• initial data findings ✅

• raw data ❌

• changelogs ❌

Explanation:
Sharing early insights lets stakeholders correct direction before deep analysis.

---

Question 8

Using PACE for mental-health EDA helps achieve: (Select all)

• Modify data to meet deadlines ❌

• Confirm dataset represents enough European regions. ✅

• Ensure ethical depiction of subjects. ✅

• Maintain focus on key priorities and goals. ✅

Explanation:
PACE helps evaluate completeness, ethics, and project alignment.

---

Question 9

Radiologist reviewing X-rays is an example of:

• Human augmentation ✅

• Input validation ❌

• Reproducibility ❌

• Bias evaluation ❌

Explanation:
AI supports the human expert, not replaces them — a classic human-in-the-loop safeguard.

---

Question 10

Why is the line graph misleading? (Select all)

• It’s unethical to compare unemployment between administrations ❌ (not inherently unethical)

• It doesn’t label the y-axis. ✅

• It is unnecessarily speculative with extreme predictions. ✅

• X-axis spacing changes from every 2 years to yearly. ✅

Explanation:
The graph hides scale (missing y-axis), changes spacing, and exaggerates speculative data.

---

🧾 Summary Table

---