Graded Quiz: Model Development: :Data Analysis with Python (Applied Data Science Specialization) Answers 2025

1. Question 1

What does LinearRegression() do?

• ❌ Assigns a linear regression model to the lm variable

• ❌ Fits a regression object to the variable lm

• ❌ Predicts output values of a linear regression object

• ✅ Creates a linear regression object and stores it in the lm variable

Explanation:
LinearRegression() initializes/creates a linear regression model object. It does NOT fit or predict until .fit() or .predict() is called.

2. Question 2

Residual errors consistently increase with x. What does this show?

• ❌ Highly accurate model predictions

• ✅ Residual pattern suggests that a non-linear model may be more appropriate

• ❌ Random disruption of residuals

• ❌ Regression line fits the points exactly

Explanation:
If residuals increase or follow a pattern, it violates linear assumptions. This suggests non-linearity.

3. Question 3

PolynomialFeatures(degree=3) — what is the order of polynomial features?

• ✅ Between 0 and 3, inclusive

• ❌ A maximum of 3

• ❌ A polynomial of degree 3

• ❌ A minimum of 3

Explanation:
PolynomialFeatures(degree=3) generates 1, x, x², x³, i.e., degrees from 0 → 3.

4. Question 4

Blue regression MSE area is much smaller than red mean-line MSE area. What can be inferred?

• ✅ It captures data trends well.

• ❌ It adds variations to predictions.

• ❌ It performs poorly overall.

• ❌ It copies the mean of the data.

Explanation:
Lower MSE for regression line vs mean line means the model fits the data much better than just predicting the mean.

5. Question 5

Prediction: $13,771.30 for car with 30 highway MPG. What should he do next?

• ❌ Fit the model again using the same data

• ❌ Analyze values to validate their range

• ❌ Plot results using a regression graph

• ✅ Compare values using a residual plot

Explanation:
Residual plots help check if prediction errors are acceptable, random, and meaningful.

🧾 Summary Table