AML Data Analysis & Reporting 3 — Questions and Answers
Question 1: What is the purpose of a Q-Q (quantile-quantile) plot in data analysis?
- Comparing two categorical variables
- Assessing whether data follows a theoretical distribution (Correct answer)
- Plotting feature importance rankings
- Visualizing model residuals over time
Correct answer: Assessing whether data follows a theoretical distribution
A Q-Q plot compares the quantiles of sample data against a theoretical distribution (e.g., normal) to assess distributional fit.
Question 2: In reporting model performance for an imbalanced dataset (95% negative class), which metric is most informative?
- Accuracy
- Area Under the ROC Curve (AUC-ROC) (Correct answer)
- Mean Squared Error
- R-squared
Correct answer: Area Under the ROC Curve (AUC-ROC)
AUC-ROC evaluates discrimination ability across all thresholds and is robust to class imbalance, unlike accuracy which can be misleadingly high.
Question 3: What does a Variance Inflation Factor (VIF) greater than 10 indicate?
- High model variance
- Severe multicollinearity in that predictor (Correct answer)
- Heteroscedasticity
- Non-linear relationship
Correct answer: Severe multicollinearity in that predictor
VIF > 10 is a common threshold indicating severe multicollinearity, meaning the predictor is nearly a linear combination of others.
Question 4: Which statistical test is used to determine whether two independent samples have the same mean?
- Chi-square test
- Paired t-test
- Independent samples t-test (Correct answer)
- ANOVA
Correct answer: Independent samples t-test
The independent samples t-test compares means of two unrelated groups to determine if they differ significantly.
Question 5: A scatter plot shows a fan-shaped pattern in model residuals vs. fitted values. What does this indicate?
- Non-linearity
- Heteroscedasticity (Correct answer)
- Autocorrelation
- Overfitting
Correct answer: Heteroscedasticity
A fan-shaped residual pattern indicates heteroscedasticity, meaning residual variance increases with fitted values, violating OLS assumptions.
Question 6: In exploratory data analysis (EDA), what is the primary purpose of a correlation heatmap?
- Identifying outliers in each feature
- Visualizing pairwise linear relationships between all features (Correct answer)
- Comparing model predictions to actuals
- Showing class distribution balance
Correct answer: Visualizing pairwise linear relationships between all features
A correlation heatmap displays pairwise Pearson (or Spearman) correlations as color-coded cells, revealing linear relationships and potential multicollinearity.
Question 7: When presenting model results to a non-technical stakeholder, which reporting approach is most effective?
- Sharing the full confusion matrix with raw counts
- Reporting p-values for each coefficient
- Translating metrics into business outcomes (e.g., revenue impact) (Correct answer)
- Displaying the model's loss curve over epochs
Correct answer: Translating metrics into business outcomes (e.g., revenue impact)
Non-technical stakeholders need business-contextualized metrics (e.g., 'This model saves $200K/year in fraud losses') rather than statistical abstractions.
AML Data Analysis & Reporting 3
What is the purpose of a Q-Q (quantile-quantile) plot in data analysis?