Regression Analysis & Modeling Exam 2026: Comprehensive
University/College Practice Examination — Linear & Multiple
Regression, Correlation, Least Squares, Model Assumptions,
Residual Analysis, Hypothesis Testing, ANOVA, Prediction,
Diagnostics & Model Selection — 190 Multiple-Choice Questions
with Answers & Detailed Rationales
1. What is the primary objective of simple linear regression analysis?
A. To determine the causal relationship between two variables.
B. To model the linear relationship between a single independent variable and a dependent
variable.
C. To predict the value of an independent variable from a dependent variable.
D. To calculate the correlation coefficient between two variables.
Correct Answer: B
Explanation: Simple linear regression models the linear association between one predictor
and one continuous outcome to enable prediction and inference.
2. In the regression equation Y = β₀ + β₁X + ε, what does the term 'ε' represent?
A. The slope of the regression line.
B. The predicted value of Y.
C. The random error term.
D. The y-intercept of the regression line.
Correct Answer: C
Explanation: Epsilon (ε) represents the random, unobservable error, capturing the variation
in Y not explained by X.
,3. A researcher wants to predict a student's final GPA (on a 4.0 scale) based on their hours of
study per week. Which variable is the dependent variable?
A. Hours of study per week.
B. The student.
C. Final GPA.
D. The 4.0 scale.
Correct Answer: C
Explanation: The dependent variable is the outcome being predicted, which in this case is
the final GPA.
4. What does the coefficient of determination, R², measure?
A. The strength of the linear relationship between X and Y.
B. The proportion of the total variation in Y explained by the regression model.
C. The average error of the predictions made by the model.
D. The slope of the regression line.
Correct Answer: B
Explanation: R-squared quantifies the proportion of variance in the dependent variable
predictable from the independent variable(s).
5. In a simple linear regression, if the slope (β₁) is negative, what is the nature of the
relationship between the independent and dependent variables?
A. There is no relationship.
B. There is a positive relationship.
C. There is a negative relationship.
D. The relationship is non-linear.
Correct Answer: C
,Explanation: A negative slope indicates an inverse relationship, where an increase in the
predictor is associated with a decrease in the outcome.
**6. A company's sales (in thousands) are modeled as Sales = 50 + 5 * (Advertising Spend in
thousands). What is the predicted sales if the advertising spend is $10,000?**
A. $50,000
B. $55,000
C. $100,000
D. $105,000
Correct Answer: C
Explanation: Substituting X=10 into the equation gives Sales = 50 + 5*(10) = 100. Since sales
are in thousands, this is $100,000.
7. Which method is most commonly used to estimate the coefficients (β₀ and β₁) in a linear
regression model?
A. Maximum Likelihood Estimation (MLE)
B. Ordinary Least Squares (OLS)
C. Principal Component Analysis (PCA)
D. Ridge Regression
Correct Answer: B
Explanation: Ordinary Least Squares (OLS) is the standard method that minimizes the sum of
the squared residuals.
8. What is a key assumption of the simple linear regression model regarding the error term?
A. The error term must be constant for all observations.
B. The error term must be perfectly correlated with the independent variable.
C. The error term is assumed to have a mean of zero.
, D. The error term must follow a uniform distribution.
Correct Answer: C
Explanation: A core assumption is that the errors have a mean of zero, meaning the model is
unbiased on average.
9. What is the name of the difference between an observed value of Y and its predicted
value (Ŷ)?
A. The slope
B. The intercept
C. The residual
D. The standard error
Correct Answer: C
Explanation: A residual (e = Y - Ŷ) is the vertical distance between a data point and the
regression line.
10. A researcher finds a strong positive correlation between ice cream sales and the number
of drownings. What is the most likely explanation for this relationship?
A. Eating ice cream causes people to become complacent in the water.
B. The relationship is spurious and likely caused by a third variable, such as temperature.
C. The relationship is causal and should be used for policy-making.
D. The correlation is a coincidence with no underlying structure.
Correct Answer: B
Explanation: This is a classic example of a spurious correlation, where a confounding variable
(temperature) drives both outcomes.
11. In the context of regression, what is extrapolation?
University/College Practice Examination — Linear & Multiple
Regression, Correlation, Least Squares, Model Assumptions,
Residual Analysis, Hypothesis Testing, ANOVA, Prediction,
Diagnostics & Model Selection — 190 Multiple-Choice Questions
with Answers & Detailed Rationales
1. What is the primary objective of simple linear regression analysis?
A. To determine the causal relationship between two variables.
B. To model the linear relationship between a single independent variable and a dependent
variable.
C. To predict the value of an independent variable from a dependent variable.
D. To calculate the correlation coefficient between two variables.
Correct Answer: B
Explanation: Simple linear regression models the linear association between one predictor
and one continuous outcome to enable prediction and inference.
2. In the regression equation Y = β₀ + β₁X + ε, what does the term 'ε' represent?
A. The slope of the regression line.
B. The predicted value of Y.
C. The random error term.
D. The y-intercept of the regression line.
Correct Answer: C
Explanation: Epsilon (ε) represents the random, unobservable error, capturing the variation
in Y not explained by X.
,3. A researcher wants to predict a student's final GPA (on a 4.0 scale) based on their hours of
study per week. Which variable is the dependent variable?
A. Hours of study per week.
B. The student.
C. Final GPA.
D. The 4.0 scale.
Correct Answer: C
Explanation: The dependent variable is the outcome being predicted, which in this case is
the final GPA.
4. What does the coefficient of determination, R², measure?
A. The strength of the linear relationship between X and Y.
B. The proportion of the total variation in Y explained by the regression model.
C. The average error of the predictions made by the model.
D. The slope of the regression line.
Correct Answer: B
Explanation: R-squared quantifies the proportion of variance in the dependent variable
predictable from the independent variable(s).
5. In a simple linear regression, if the slope (β₁) is negative, what is the nature of the
relationship between the independent and dependent variables?
A. There is no relationship.
B. There is a positive relationship.
C. There is a negative relationship.
D. The relationship is non-linear.
Correct Answer: C
,Explanation: A negative slope indicates an inverse relationship, where an increase in the
predictor is associated with a decrease in the outcome.
**6. A company's sales (in thousands) are modeled as Sales = 50 + 5 * (Advertising Spend in
thousands). What is the predicted sales if the advertising spend is $10,000?**
A. $50,000
B. $55,000
C. $100,000
D. $105,000
Correct Answer: C
Explanation: Substituting X=10 into the equation gives Sales = 50 + 5*(10) = 100. Since sales
are in thousands, this is $100,000.
7. Which method is most commonly used to estimate the coefficients (β₀ and β₁) in a linear
regression model?
A. Maximum Likelihood Estimation (MLE)
B. Ordinary Least Squares (OLS)
C. Principal Component Analysis (PCA)
D. Ridge Regression
Correct Answer: B
Explanation: Ordinary Least Squares (OLS) is the standard method that minimizes the sum of
the squared residuals.
8. What is a key assumption of the simple linear regression model regarding the error term?
A. The error term must be constant for all observations.
B. The error term must be perfectly correlated with the independent variable.
C. The error term is assumed to have a mean of zero.
, D. The error term must follow a uniform distribution.
Correct Answer: C
Explanation: A core assumption is that the errors have a mean of zero, meaning the model is
unbiased on average.
9. What is the name of the difference between an observed value of Y and its predicted
value (Ŷ)?
A. The slope
B. The intercept
C. The residual
D. The standard error
Correct Answer: C
Explanation: A residual (e = Y - Ŷ) is the vertical distance between a data point and the
regression line.
10. A researcher finds a strong positive correlation between ice cream sales and the number
of drownings. What is the most likely explanation for this relationship?
A. Eating ice cream causes people to become complacent in the water.
B. The relationship is spurious and likely caused by a third variable, such as temperature.
C. The relationship is causal and should be used for policy-making.
D. The correlation is a coincidence with no underlying structure.
Correct Answer: B
Explanation: This is a classic example of a spurious correlation, where a confounding variable
(temperature) drives both outcomes.
11. In the context of regression, what is extrapolation?
