Statistics: Simple Linear and Binary Logistic Regression
True or False Questions
1. Correlation analysis measures the causal relationship between two variables. (False)
2. The regression line is always linear. (False)
3. Pearson's r is used to measure the degree of linear relationship between two variables. (True)
4. The coefficient of determination (R^2) indicates the percentage of variation in the dependent
variable explained by the independent variable. (True)
5. A scatter plot is useful to assess the linearity between variables. (True)
6. In a simple linear regression, more than one independent variable is used. (False)
7. The intercept in a regression equation always has a meaningful interpretation. (False)
8. Binary logistic regression is appropriate for a categorical dependent variable. (True)
9. Residual plots can help verify assumptions of regression. (True)
10. The Durbin-Watson statistic detects multicollinearity. (False)
Multiple Choice Questions
1. Which of the following is NOT an assumption of linear regression?
A. Linearity
B. Independence of errors
C. Homogeneity of variance
D. Multicollinearity (D)
2. What does the slope (b1) in a regression equation represent?
A. The average value of Y
B. The change in Y for a one-unit change in X
C. The error term
D. The intercept (B)
Page 1
Statistics: Simple Linear and Binary Logistic Regression
3. What does an R^2 value of 0.75 mean?
A. 75% of the variance in X is explained by Y
B. 75% of the variance in Y is explained by X
C. The model is not significant
D. The slope is 0.75 (B)
4. The function =CORREL(array1, array2) in Excel is used to:
A. Calculate mean
B. Calculate correlation coefficient
C. Calculate regression
D. Perform hypothesis testing (B)
5. If residuals are not normally distributed, which of the following is NOT a suggested solution?
A. Increase sample size
B. Use logarithmic transformation
C. Ignore the problem
D. Remove all data points (D)
6. Which plot is commonly used to assess normality of residuals?
A. Line plot
B. Q-Q plot
C. Bar chart
D. Scatter plot (B)
7. What does a Durbin-Watson statistic close to 2 indicate?
A. Negative autocorrelation
B. Positive autocorrelation
C. No autocorrelation
D. Strong correlation (C)
Page 2
Statistics: Simple Linear and Binary Logistic Regression
8. The equation Y = 49.477 + 1.9641X suggests:
A. X has a negative effect on Y
B. Each increase in X by 1 increases Y by 1.9641
C. Intercept is not interpretable
D. X has no effect on Y (B)
9. A high p-value (> 0.05) in a regression slope test indicates:
A. Reject the null hypothesis
B. Evidence of significant effect
C. No sufficient evidence of effect
D. Strong correlation (C)
10. Homoskedasticity refers to:
A. Constant error mean
B. Constant variance of errors
C. Errors being zero
D. Equal means of Y (B)
Page 3
