Scribd
Upload
562 views

Review-Multiple Regression-Multiple Choice

This document contains 30 multiple choice questions about regression analysis. It covers topics like the definitions of regression, correlation, residuals, and other key regression terminology. It also addresses questions related to simple linear regression, multiple linear regression, and logistic regression models including questions about coefficients, significance testing, and model fit.

Uploaded by

Nguyễn Tuấn Anh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
562 views

Review-Multiple Regression-Multiple Choice

This document contains 30 multiple choice questions about regression analysis. It covers topics like the definitions of regression, correlation, residuals, and other key regression terminology. It also addresses questions related to simple linear regression, multiple linear regression, and logistic regression models including questions about coefficients, significance testing, and model fit.

Uploaded by

Nguyễn Tuấn Anh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Review Multi-regression

1. Constructing a mathematical model that can be used to predict one variable by another is
called which of the following?
a. Hypothesis testing
b. Statistical prediction
c. Correlation analysis
d. Regression

2. A measure of the degree of relatedness between two variables is called which of the
following?
a. Residual
b. Regression
c. Correlation
d. Confidence

3. What does the Y intercept (b0) represent?


a. The predicted value of Y when X = 0.
b. The variation around the line of regression.
c. The estimated change in average Y per unit change in X.
d. The predicted value of Y

4. In linear regression, the variable being predicted is usually called which of the following?
a. Explanatory variable
b. Independent variable
c. Predictor variable
d. Dependent variable

5. What does the standard error of the estimate measure?


a. The variation explained by the model
b. The total variation of the Y variable
c. The variation around the regression line
d. The variation of the X variable

6. What information is provided by the coefficient of determination?


a. Whether r has any significance
b. The coefficient of correlation is larger than one
c. Whether total variation should be partitioned
d. The proportion of total variation in Y that is explained by X

7. What do residuals represent?


a. The difference between the predicted Y values and the mean of Y
b. The difference between the actual Y values and the mean of Y
c. The difference between the actual Y values and the predicted Y values
d. The predicted value of Y for the average X value

8. Assuming a linear relationship between X and Y, which of the following is true if the coefficient of
correlation (r) equals -0.35?
a. Variable X is larger than variable Y
b. The variance is negative
c. The slope is negative
d. There is no correlation

9. The width of the confidence interval estimate for the predicted value of Y depends on which
of the following?
a. Standard error of the estimate
b. Value X for which the prediction is being made
c. Sample size
d. All of the above

10. The width of the confidence interval estimate for the predicted value of Y depends on which
of the following?
a. Standard error of the estimate
b. Value X for which the prediction is being made
c. Sample size
d. All of the above

11. A 95% confidence interval for b1 is determined to be (15, 30). Interpret the meaning of this
interval.
a. You can be 95% confident that the X value will increase by between 15 and 30 units
for every one unit increase in Y.
b. At the 5% level of significance, there is no evidence of a linear relationship between X
and Y.
c. You can be 95% confident that the mean value of Y will fall between 15 and 30 units.
d. You can be 95% confident that the average value of Y will increase by between 15 and
30 units for every one unit increase in X.
12. Which of the following indicates the reason for using least squares as a method for determining the
regression coefficients.
a. Squaring acts as a penalty for large errors.
b. Any other values chosen for b0 and b1 will have a larger sum of squared residuals.
c. The sum of the errors is simply equal to 0.
d. All of the above.

13. The following data is used to construct a regression model:

Which of the following values indicates the slope?


a. 3
b. 2.5
c. 2.25
d. 2

14. The following data is used to construct a regression model:

a. 2.5
b. 2
c. 2.25
d. 3

15. The following data is used to construct a regression model:

Which of the following values indicates the coefficient of determination?


a. 0.9
b. 0.85
c. 0.8
d. 0.95

16. Values of adjusted r2 will always be less than the “regular” r2 coefficient of multiple
determination.
a. True
b. False
17. The adjusted coefficient of multiple determination adjusts for the number of independent
variables in the regression equation.
a. True
b. False

18. The coefficient of multiple determination is calculated for each independent variable and
determines the proportion of the variation in Y due to the variable tested.
a. True
b. False

19. A multiple linear regression model constructed using a sample size of 25 and 4 explanatory
variables will have 20 error degrees of freedom.

a. True
b. False

20. The null hypothesis for the test of significance of the regression model is that at least one
coefficient is equal to a constant, c.

a. True
b. False

21. The overall F test for a significant relationship between Y and the set of independent
variables (X) has the same equation and degrees of freedom as that for the simple linear
regression model.

a. True
b. False

22. The critical value for the test of significance of the regression model is based on the F
statistic having n – k – 1 numerator degrees of freedom and k denominator degrees of freedom.

a. True
b. False

23. Where β1 is the slope of X1 in a simple linear regression model, in the multiple regression
model it represents the slope of Y with X1 when holding all other Xs constant.

a. True
b. False
24. Any independent variable that does not significantly reduce the error in predicting Y may be
eliminated.

a. True
b. False

25. The null hypothesis for the partial F test to determine if an independent variable makes a
significant contribution to reducing the error in predicting Y is that adding the independent
variable significantly improves the model after other independent variables are included.

a. True
b. False

26. The relationship between the t and F statistics in the multiple regression model is t = F2.

a. True
b. False

27. Multiple linear regression models assume that all variables are numeric. If a variable is
categorical, dummy variables may be used to apply the regression model.

a. True
b. False

28. An interaction between two independent variables can adversely affect the multiple
regression model.

a. True
b. False

29. If an independent variable is categorical, use logistic regression.

a. True
b. False
30. The deviance statistic is used to determine if the logistic regression model is a good fit for the
data.

a. True
b. False

You might also like