WGU D600 - STATISTICAL DATA MINING TASK 1 | MULTIPLE
LINEAR REGRESSION ANALYSIS | COMPLETE PERFORMANCE
ASSESSMENT WITH PYTHON, MODEL REDUCTION &
DIAGNOSTICS | 2026 UPDATED
147 Questions with Answers and Detailed Rationales
100 PERCENT GUARANTEED PASS
INSTANT DOWNLOAD ANSWERS INCLUDED
IMPORTANCE OF THIS DOCUMENT
This comprehensive examination preparation guide has been meticulously developed to help you succeed in the
WGU D600 - STATISTICAL DATA MINING TASK 1 | MULTIPLE LINEAR REGRESSION ANALYSIS | COMPLETE
PERFORMANCE ASSESSMENT WITH PYTHON, MODEL REDUCTION & DIAGNOSTICS | 2026 UPDATED. It
contains 147 carefully selected questions that reflect the most current exam content and testing strategies. Each
question is accompanied by a correct answer and a detailed rationale that explains the underlying
pathophysiology, pharmacology, or clinical reasoning.
Self-Assessment – Test your knowledge and Exam Preparation – Familiarize yourself with the
identify areas requiring further question format and content
study areas
Concept Reinforcement – Deepen your Confidence Building – Develop test-taking
understanding through strategies and reduce
evidence-based exam anxiety
rationales
Time Management – Practice answering
questions under simulated
exam conditions
Review Summary 147 Questions
Foundations - Application - WGU D600 Statistical DATA Mining TASK 1 Multiple Linear Regression Analysis
Complete Performance Assessment WITH Python Model Reduction & Diagnostics 2026 Updated Statistical
DATA Mining Multiple Linear Regression Model Reduction & Diagnostics Undergraduate YEAR
Upper-division WGU / LAS Vegas College Equivalent
All answers with rationales
,Table of Contents
Content Area Questions Key Topics
Multiple Linear Regression 1-25 Model, Regression, Multiple, Predictors, Analyst
Model Specification AND
Assumptions
DATA Preparation 26-50 Regression, Multiple, Model, Predictors, Interpretation
Exploratory DATA Analysis
AND Variable Selection
Model Estimation AND 51-75 Regression, Model, Multiple, Linear, Predictors
Interpretation OF
Coefficients
Model Reduction AND 76-100 Regression, Model, Multiple, Appropriate, Linear
Variable Selection
Techniques
Multicollinearity Detection 101-125 Regression, Model, Multiple, Predictors, Appropriate
AND Remediation
Regression Diagnostics 126-147 Regression, Predictors, Multiple, Model, Analyst
Linearity Normality
Homoscedasticity
Independence
TOTAL 147 All questions include answers and detailed rationales
,Section A - Multiple Linear Regression Model Specification
AND Assumptions
Q1.
A data miner fits an OLS model in statsmodels and observes that adding a highly
correlated predictor raises R² slightly but inflates the standard error of an existing
coefficient. Which diagnostic best confirms this issue?
A. Durbin-Watson statistic near 2.0 B. Variance Inflation Factor (VIF) above 10
for the correlated predictors
C. Breusch-Pagan test p-value > 0.05 D. Cook's distance below 4/n for all rows
Correct: B - Variance Inflation Factor (VIF) above 10 for the correlated predictors
Rationale:VIF quantifies how much a predictor's variance is inflated by linear dependence on
other predictors; values above ~10 signal serious multicollinearity. Durbin-Watson and
Breusch-Pagan address autocorrelation and heteroscedasticity respectively, and Cook's
distance addresses influence, not collinearity.
Why the other answers are wrong:
A. Durbin-Watson detects residual autocorrelation, not predictor collinearity.
C. Breusch-Pagan tests for heteroscedasticity; a non-significant p-value indicates
homoscedasticity, unrelated to VIF.
D. Cook's distance flags influential observations, not multicollinearity among predictors.
Reference: James, G. et al. (2023). An Introduction to Statistical Learning, 2nd Ed., Ch. 3 & 6.
Q2.
In a multiple regression predicting home price, the coefficient on square footage is 145
with a 95% CI of [120, 170]. Which interpretation is most defensible?
A. Holding other predictors constant, each B. Square footage explains 145% of the
additional square foot is associated with an variation in price.
expected $145 increase in price.
C. The average home price increases by D. The probability that square footage
$145 for every additional square foot affects price is 95%.
regardless of other variables.
Correct: A - Holding other predictors constant, each additional square foot is associated
with an expected $145 increase in price.
Rationale:In multiple regression, each coefficient is a partial effect: the expected change in Y
per one-unit change in X, holding all other predictors fixed. The CI describes precision of that
partial slope, not variance explained or a probability statement about the coefficient.
Page 3
, Section A - Multiple Linear Regression Model Specification AND Assumptions
Why the other answers are wrong:
B. Coefficients are not variance-explained measures; R² plays that role.
C. Omitting the ceteris paribus condition misstates the partial-effect interpretation.
D. Frequentist CIs are not posterior probabilities that the coefficient affects the outcome.
Reference: James, G. et al. (2023). An Introduction to Statistical Learning, 2nd Ed., Ch. 3.
Q3.
An analyst compares two nested models using an F-test and obtains p = 0.42. Which
conclusion is most appropriate for model reduction?
A. Retain the larger model because it has B. Reject the reduced model and add
higher R². interaction terms.
C. Fail to reject the reduced model; the D. The test is invalid because nested
dropped predictors do not significantly models cannot be compared with F.
improve fit.
Correct: C - Fail to reject the reduced model; the dropped predictors do not significantly
improve fit.
Rationale:A non-significant partial F-test indicates the additional predictors do not
significantly improve explanatory power, supporting the parsimonious reduced model. Higher
R² alone is expected when adding predictors and does not justify retention.
Why the other answers are wrong:
A. R² mechanically increases with added predictors; significance testing is required.
B. The F-test result does not motivate adding interactions.
D. Nested models are precisely the setting where the partial F-test is valid.
Reference: Kutner, M. et al. (2019). Applied Linear Statistical Models, 5th Ed., Ch. 7.
Q4.
Which statement correctly contrasts AIC and adjusted R² for model selection in a
data-mining workflow?
A. AIC penalizes complexity and targets B. Both metrics are scale-free and can be
predictive likelihood; adjusted R² penalizes compared across different response
complexity but is bounded by 1 and oriented transformations.
to in-sample fit.
C. AIC requires nested models; adjusted R² D. Adjusted R² can decrease when a truly
does not. relevant predictor is added.
Correct: A - AIC penalizes complexity and targets predictive likelihood; adjusted R²
penalizes complexity but is bounded by 1 and oriented to in-sample fit.
Page 4
LINEAR REGRESSION ANALYSIS | COMPLETE PERFORMANCE
ASSESSMENT WITH PYTHON, MODEL REDUCTION &
DIAGNOSTICS | 2026 UPDATED
147 Questions with Answers and Detailed Rationales
100 PERCENT GUARANTEED PASS
INSTANT DOWNLOAD ANSWERS INCLUDED
IMPORTANCE OF THIS DOCUMENT
This comprehensive examination preparation guide has been meticulously developed to help you succeed in the
WGU D600 - STATISTICAL DATA MINING TASK 1 | MULTIPLE LINEAR REGRESSION ANALYSIS | COMPLETE
PERFORMANCE ASSESSMENT WITH PYTHON, MODEL REDUCTION & DIAGNOSTICS | 2026 UPDATED. It
contains 147 carefully selected questions that reflect the most current exam content and testing strategies. Each
question is accompanied by a correct answer and a detailed rationale that explains the underlying
pathophysiology, pharmacology, or clinical reasoning.
Self-Assessment – Test your knowledge and Exam Preparation – Familiarize yourself with the
identify areas requiring further question format and content
study areas
Concept Reinforcement – Deepen your Confidence Building – Develop test-taking
understanding through strategies and reduce
evidence-based exam anxiety
rationales
Time Management – Practice answering
questions under simulated
exam conditions
Review Summary 147 Questions
Foundations - Application - WGU D600 Statistical DATA Mining TASK 1 Multiple Linear Regression Analysis
Complete Performance Assessment WITH Python Model Reduction & Diagnostics 2026 Updated Statistical
DATA Mining Multiple Linear Regression Model Reduction & Diagnostics Undergraduate YEAR
Upper-division WGU / LAS Vegas College Equivalent
All answers with rationales
,Table of Contents
Content Area Questions Key Topics
Multiple Linear Regression 1-25 Model, Regression, Multiple, Predictors, Analyst
Model Specification AND
Assumptions
DATA Preparation 26-50 Regression, Multiple, Model, Predictors, Interpretation
Exploratory DATA Analysis
AND Variable Selection
Model Estimation AND 51-75 Regression, Model, Multiple, Linear, Predictors
Interpretation OF
Coefficients
Model Reduction AND 76-100 Regression, Model, Multiple, Appropriate, Linear
Variable Selection
Techniques
Multicollinearity Detection 101-125 Regression, Model, Multiple, Predictors, Appropriate
AND Remediation
Regression Diagnostics 126-147 Regression, Predictors, Multiple, Model, Analyst
Linearity Normality
Homoscedasticity
Independence
TOTAL 147 All questions include answers and detailed rationales
,Section A - Multiple Linear Regression Model Specification
AND Assumptions
Q1.
A data miner fits an OLS model in statsmodels and observes that adding a highly
correlated predictor raises R² slightly but inflates the standard error of an existing
coefficient. Which diagnostic best confirms this issue?
A. Durbin-Watson statistic near 2.0 B. Variance Inflation Factor (VIF) above 10
for the correlated predictors
C. Breusch-Pagan test p-value > 0.05 D. Cook's distance below 4/n for all rows
Correct: B - Variance Inflation Factor (VIF) above 10 for the correlated predictors
Rationale:VIF quantifies how much a predictor's variance is inflated by linear dependence on
other predictors; values above ~10 signal serious multicollinearity. Durbin-Watson and
Breusch-Pagan address autocorrelation and heteroscedasticity respectively, and Cook's
distance addresses influence, not collinearity.
Why the other answers are wrong:
A. Durbin-Watson detects residual autocorrelation, not predictor collinearity.
C. Breusch-Pagan tests for heteroscedasticity; a non-significant p-value indicates
homoscedasticity, unrelated to VIF.
D. Cook's distance flags influential observations, not multicollinearity among predictors.
Reference: James, G. et al. (2023). An Introduction to Statistical Learning, 2nd Ed., Ch. 3 & 6.
Q2.
In a multiple regression predicting home price, the coefficient on square footage is 145
with a 95% CI of [120, 170]. Which interpretation is most defensible?
A. Holding other predictors constant, each B. Square footage explains 145% of the
additional square foot is associated with an variation in price.
expected $145 increase in price.
C. The average home price increases by D. The probability that square footage
$145 for every additional square foot affects price is 95%.
regardless of other variables.
Correct: A - Holding other predictors constant, each additional square foot is associated
with an expected $145 increase in price.
Rationale:In multiple regression, each coefficient is a partial effect: the expected change in Y
per one-unit change in X, holding all other predictors fixed. The CI describes precision of that
partial slope, not variance explained or a probability statement about the coefficient.
Page 3
, Section A - Multiple Linear Regression Model Specification AND Assumptions
Why the other answers are wrong:
B. Coefficients are not variance-explained measures; R² plays that role.
C. Omitting the ceteris paribus condition misstates the partial-effect interpretation.
D. Frequentist CIs are not posterior probabilities that the coefficient affects the outcome.
Reference: James, G. et al. (2023). An Introduction to Statistical Learning, 2nd Ed., Ch. 3.
Q3.
An analyst compares two nested models using an F-test and obtains p = 0.42. Which
conclusion is most appropriate for model reduction?
A. Retain the larger model because it has B. Reject the reduced model and add
higher R². interaction terms.
C. Fail to reject the reduced model; the D. The test is invalid because nested
dropped predictors do not significantly models cannot be compared with F.
improve fit.
Correct: C - Fail to reject the reduced model; the dropped predictors do not significantly
improve fit.
Rationale:A non-significant partial F-test indicates the additional predictors do not
significantly improve explanatory power, supporting the parsimonious reduced model. Higher
R² alone is expected when adding predictors and does not justify retention.
Why the other answers are wrong:
A. R² mechanically increases with added predictors; significance testing is required.
B. The F-test result does not motivate adding interactions.
D. Nested models are precisely the setting where the partial F-test is valid.
Reference: Kutner, M. et al. (2019). Applied Linear Statistical Models, 5th Ed., Ch. 7.
Q4.
Which statement correctly contrasts AIC and adjusted R² for model selection in a
data-mining workflow?
A. AIC penalizes complexity and targets B. Both metrics are scale-free and can be
predictive likelihood; adjusted R² penalizes compared across different response
complexity but is bounded by 1 and oriented transformations.
to in-sample fit.
C. AIC requires nested models; adjusted R² D. Adjusted R² can decrease when a truly
does not. relevant predictor is added.
Correct: A - AIC penalizes complexity and targets predictive likelihood; adjusted R²
penalizes complexity but is bounded by 1 and oriented to in-sample fit.
Page 4
