WGU D600 Exam 2 : Logistic Regression
Analysis | Complete Report, Python
Modeling, Confusion Matrix & Results |
2026/2027 {JUST RELEASED} Updated
Practice Question Bank & Answer Rationale
THIS PACK CONTAINS
49 exam-style multiple-choice questions. Each question includes the correct answer and a complete rationale
for focused revision.
COVERAGE
This exam assesses graduate-level competency in logistic regression analysis, including data preparation,
Python modeling with statsmodels and scikit-learn, model interpretation, confusion matrix evaluation, and
results reporting. It emphasizes practical application, reproducibility, and critical evaluation of classification
models.
STUDY GUIDE
Recommended duration: 3 hours. Passing target: 80%.
HIGHP - Page 1 of 17
,1. In the D600 Task 2 analysis, which statement best justifies the research question's
business relevance?
[ ] A. The research question explores how housing features predict luxury classification to inform pricing
and investment decisions.
[ ] B. The research question aims to determine the causal effect of square footage on price using linear
regression.
[ ] C. The research question focuses on clustering homes into luxury and non-luxury segments using
unsupervised learning.
[ ] D. The research question investigates the impact of renovation quality on property tax assessments.
CORRECT: A. The research question explores how housing features predict luxury classification to
inform pricing and investment decisions.
The research question in the report explicitly addresses predicting luxury classification from housing features
for business decision-making. Option B is incorrect because the analysis uses logistic regression, not linear
regression. Option C is incorrect as the method is supervised classification, not clustering. Option D is not
mentioned in the report.
2. Which of the following best describes the purpose of the descriptive statistics
computed in Section C2?
[ ] A. To summarize the distribution and central tendency of variables, aiding in understanding data
characteristics and guiding modeling decisions.
[ ] B. To test the statistical significance of each predictor variable before model fitting.
[ ] C. To transform categorical variables into dummy variables for logistic regression.
[ ] D. To evaluate the model's predictive accuracy on the test set.
CORRECT: A. To summarize the distribution and central tendency of variables, aiding in
understanding data characteristics and guiding modeling decisions.
Descriptive statistics provide summary measures like mean, standard deviation, and quartiles to understand
data distribution and balance. Option B is incorrect because significance testing occurs during model fitting.
Option C refers to encoding, not descriptive statistics. Option D relates to model evaluation, not descriptive
statistics.
3. In the D600 Task 2 report, the dataset was split into training (75%) and test (25%) sets.
Which scikit-learn function is most appropriate for this split?
[ ] A. train_test_split
[ ] B. cross_val_score
[ ] C. GridSearchCV
[ ] D. StratifiedKFold
CORRECT: A. train_test_split
The train_test_split function from scikit-learn is commonly used to split data into training and test sets. Option
HIGHP - Page 2 of 17
, B is for cross-validation scoring, not splitting. Option C is for hyperparameter tuning. Option D is for
cross-validation folds, not a simple split.
4. The model optimization used backward stepwise elimination with a p-value threshold of
0.05. What is the primary goal of this technique?
[ ] A. To remove statistically insignificant predictors and improve model parsimony.
[ ] B. To increase the model's training accuracy by including all variables.
[ ] C. To reduce overfitting by adding interaction terms.
[ ] D. To transform the dependent variable into a linear scale.
CORRECT: A. To remove statistically insignificant predictors and improve model parsimony.
Backward stepwise elimination removes predictors with p-values above a threshold to retain only significant
variables, enhancing model interpretability and parsimony. Option B is the opposite. Option C is unrelated.
Option D is incorrect as logistic regression models a binary outcome, not transforming it to linear.
5. In logistic regression, what does an odds ratio of 1.5 for a predictor indicate?
[ ] A. A one-unit increase in the predictor multiplies the odds of the outcome by 1.5, holding other
variables constant.
[ ] B. The predictor increases the probability of the outcome by 1.5 percentage points.
[ ] C. The predictor is not statistically significant at the 0.05 level.
[ ] D. The model's overall accuracy increases by 1.5% when the predictor is added.
CORRECT: A. A one-unit increase in the predictor multiplies the odds of the outcome by 1.5, holding
other variables constant.
An odds ratio of 1.5 means the odds of the outcome are 1.5 times higher for each one-unit increase in the
predictor, all else equal. Option B confuses odds with probability. Option C is unrelated to significance. Option
D confuses odds ratio with accuracy improvement.
6. When evaluating a logistic regression model, which metric is most appropriate for
imbalanced classes?
[ ] A. Area under the ROC curve (AUC)
[ ] B. Accuracy
[ ] C. Mean squared error
[ ] D. R-squared
CORRECT: A. Area under the ROC curve (AUC)
AUC is robust to class imbalance as it evaluates ranking across thresholds. Accuracy (B) can be misleading
when classes are imbalanced. MSE (C) and R-squared (D) are for regression, not classification.
HIGHP - Page 3 of 17
Analysis | Complete Report, Python
Modeling, Confusion Matrix & Results |
2026/2027 {JUST RELEASED} Updated
Practice Question Bank & Answer Rationale
THIS PACK CONTAINS
49 exam-style multiple-choice questions. Each question includes the correct answer and a complete rationale
for focused revision.
COVERAGE
This exam assesses graduate-level competency in logistic regression analysis, including data preparation,
Python modeling with statsmodels and scikit-learn, model interpretation, confusion matrix evaluation, and
results reporting. It emphasizes practical application, reproducibility, and critical evaluation of classification
models.
STUDY GUIDE
Recommended duration: 3 hours. Passing target: 80%.
HIGHP - Page 1 of 17
,1. In the D600 Task 2 analysis, which statement best justifies the research question's
business relevance?
[ ] A. The research question explores how housing features predict luxury classification to inform pricing
and investment decisions.
[ ] B. The research question aims to determine the causal effect of square footage on price using linear
regression.
[ ] C. The research question focuses on clustering homes into luxury and non-luxury segments using
unsupervised learning.
[ ] D. The research question investigates the impact of renovation quality on property tax assessments.
CORRECT: A. The research question explores how housing features predict luxury classification to
inform pricing and investment decisions.
The research question in the report explicitly addresses predicting luxury classification from housing features
for business decision-making. Option B is incorrect because the analysis uses logistic regression, not linear
regression. Option C is incorrect as the method is supervised classification, not clustering. Option D is not
mentioned in the report.
2. Which of the following best describes the purpose of the descriptive statistics
computed in Section C2?
[ ] A. To summarize the distribution and central tendency of variables, aiding in understanding data
characteristics and guiding modeling decisions.
[ ] B. To test the statistical significance of each predictor variable before model fitting.
[ ] C. To transform categorical variables into dummy variables for logistic regression.
[ ] D. To evaluate the model's predictive accuracy on the test set.
CORRECT: A. To summarize the distribution and central tendency of variables, aiding in
understanding data characteristics and guiding modeling decisions.
Descriptive statistics provide summary measures like mean, standard deviation, and quartiles to understand
data distribution and balance. Option B is incorrect because significance testing occurs during model fitting.
Option C refers to encoding, not descriptive statistics. Option D relates to model evaluation, not descriptive
statistics.
3. In the D600 Task 2 report, the dataset was split into training (75%) and test (25%) sets.
Which scikit-learn function is most appropriate for this split?
[ ] A. train_test_split
[ ] B. cross_val_score
[ ] C. GridSearchCV
[ ] D. StratifiedKFold
CORRECT: A. train_test_split
The train_test_split function from scikit-learn is commonly used to split data into training and test sets. Option
HIGHP - Page 2 of 17
, B is for cross-validation scoring, not splitting. Option C is for hyperparameter tuning. Option D is for
cross-validation folds, not a simple split.
4. The model optimization used backward stepwise elimination with a p-value threshold of
0.05. What is the primary goal of this technique?
[ ] A. To remove statistically insignificant predictors and improve model parsimony.
[ ] B. To increase the model's training accuracy by including all variables.
[ ] C. To reduce overfitting by adding interaction terms.
[ ] D. To transform the dependent variable into a linear scale.
CORRECT: A. To remove statistically insignificant predictors and improve model parsimony.
Backward stepwise elimination removes predictors with p-values above a threshold to retain only significant
variables, enhancing model interpretability and parsimony. Option B is the opposite. Option C is unrelated.
Option D is incorrect as logistic regression models a binary outcome, not transforming it to linear.
5. In logistic regression, what does an odds ratio of 1.5 for a predictor indicate?
[ ] A. A one-unit increase in the predictor multiplies the odds of the outcome by 1.5, holding other
variables constant.
[ ] B. The predictor increases the probability of the outcome by 1.5 percentage points.
[ ] C. The predictor is not statistically significant at the 0.05 level.
[ ] D. The model's overall accuracy increases by 1.5% when the predictor is added.
CORRECT: A. A one-unit increase in the predictor multiplies the odds of the outcome by 1.5, holding
other variables constant.
An odds ratio of 1.5 means the odds of the outcome are 1.5 times higher for each one-unit increase in the
predictor, all else equal. Option B confuses odds with probability. Option C is unrelated to significance. Option
D confuses odds ratio with accuracy improvement.
6. When evaluating a logistic regression model, which metric is most appropriate for
imbalanced classes?
[ ] A. Area under the ROC curve (AUC)
[ ] B. Accuracy
[ ] C. Mean squared error
[ ] D. R-squared
CORRECT: A. Area under the ROC curve (AUC)
AUC is robust to class imbalance as it evaluates ranking across thresholds. Accuracy (B) can be misleading
when classes are imbalanced. MSE (C) and R-squared (D) are for regression, not classification.
HIGHP - Page 3 of 17
