ARSI UNIVERSITY

UNIVERSITY OF APPLIED SIENCES

COLLEGE OF AGRICULTURAL & ENVIROMENTAL SCIENCES
Econometrics Final Examination (2024 Academic Year)
3rd Year, 2nd Semester AgEc Department
Date: Monday, 16 December 2024
Time allotted: 2:00
Mark: 50%
IDNO______________Sign___________
Name _____________________________________________________
PART I: MULTIPLE CHOICE. (31.5 pts)
Choose the one best answer from the options provided by encircling the letter corresponding to
your choice.(1.5 pts each)

1. Which of the following conclusions is NOT equivalent to rejecting the null hypothesis?
A. The results are statistically significant. C. The alternative hypothesis is accepted.
B. The results are not statistically D. The p-value ≤ alpha (the significance
significant. level)
2. Which one of the following is /are the causes of hetroskedacity problem?
A. Existence of outliers.
B. Misspecification of a model.
C. Incorrect data transformation and incorrect functional form
D. All of the above
3. If the error term is correlated with any of the independent variables, the OLS estimators
are__________?
A. Biased and consistence C. Unbiased and inconsistence
B. Unbiased and consistence D. Biased and inconsistence
4. Variables used to incorporate qualitative information in a regression model?
A. Dummy C. Quantitative
B. Continuous D. Binomial
5. What is the main implication of the Gauss-Markov Theorem in econometrics?
A. Estimators are always unbiased
B. Ordinary Least Squares (OLS) estimators are the best linear unbiased estimators
(BLUE)
C. The dependent variable has no linear relationship with the independent variable
D. Multicollinearity does not affect OLS estimates
6. Which of the following statements about multicollinearity is true?
A. Multicollinearity violates the assumption of zero covariance between error terms and
explanatory variables.
B. Multicollinearity results in unbiased OLS estimates but increases their variances.
C. Perfect multicollinearity allows for unique parameter estimation in a regression model.
D. The presence of multicollinearity is best detected using the Breusch-Pagan test.

1
7. The purpose of using dummy variables in regression models is to:
A. Test for multicollinearity
B. Represent categorical data numerically
C. Identify outliers in the data
D. Test for autocorrelation
8. Which of the following is a key assumption in multiple regression analysis?
A. Dependent variable is categorical B. Independent variables have a constant
relationship C. No autocorrelation exists among disturbance terms D. Residuals are not
related to the explanatory variable
9. If the Variance Inflation Factor (VIF) of an independent variable exceeds 10, it implies that:
A. There is no evidence of multicollinearity.
B. The variable is perfectly correlated with the dependent variable.
C. The variable exhibits a high degree of multicollinearity with other explanatory
variables.
D. The OLS estimates will necessarily be biased.
10. What does the Breusch-Pagan test assess in a regression analysis?
A. The normality of residuals
B. The presence of autocorrelation
C. The presence of heteroscedasticity
D. The significance of regression coefficients
11. What does the "base category" represent in a regression model with dummy variables?
A. The category with the largest sample size
B. The category that is omitted to avoid multicollinearity
C. The category with the highest mean response
D. The default category used to calculate interaction effects
12. In an ANOVA table, the calculated F-statistic is given by the formula:
A) B) C) D)
13. In a simple regression with an intercept ̂ = + , the estimated slope coefficient
is equal to zero. Then the coefficient of determination (R2) is
A. 1 C. -1
B. 1 or 0 D. 0
14. If a qualitative variable like "Gender" is coded as a dummy variable, what values can
it take?
A. Any integer values C. Binary values, such as 0 and 1
B. Continuous values between 0 and 1 D. Any real number values
15. What is the dummy variable trap?
A. A situation where all dummy variables are set to 0
B. A situation where including all categories of a dummy variable leads to exact
linear dependence among regressors.
C. A trap where dummy variables cannot be used in regression
D. A situation where the regression model has too many independent variables

2
 16. To avoid the dummy variable trap, we should include all dummy variables and drop
the intercept term from the model. A True B. False
17. If a qualitative variable has m categories, how many dummy variables should be included in
the regression model to avoid the dummy variable trap?
2
A. m
C. m.(1- )
B. m.(1+ )
D. 2m
18. Consider the following regression equation: Y = β0+ β1X1+ …+ Kxk + u, In which
of the following cases, the dependent variable is binary?
A. Y indicates the gross domestic product of a country
B. Y indicates whether an adult is a college dropout
C. Y indicates household consumption expenditure
D. Y indicates the number of children in a family
19. If the coefficient of determination is 0.81, the correlation coefficient is
A. 0.9 C. -0.9
B. 0.9 or - 0.9 D. 0.56 or -0.56
20. Durbin Watson test is associated with:
A. Heteroscedasticity C. Autocorrelation
B. Multicollinearity D. Both
21. Which of the following is Odd?
A. Error term B. Constant term C. Stochastic term D. Disturbance term

PART II:(14 pts)

Workout
Show the necessary steps for each question!
Compute the following question by using matrix approach to linear regression model
1) The Regression Coefficients β ( 0, 1 and 2). (3pts)
2) The variance of covariance of β ( 0, 1 and 2). ( 3pts)
3) Coefficients of determination by using matric form (R2) and interpret its value.(2pts)
4) Adjusted R square ( ̅ 2). (2pts)
5) The Residual Sum Squares (∑ ). (1pt)
6) The Variance of the Error Term (σ2). (1pt)
7) Run the significance test of regression coefficients by using the F-test method. (2pts)
Number of observation Y X₁ X₂
1. 9 1 7
2. 11 4 9
3. 13 5 11
4. 14 6 13
5. 16 9 16
6. 17 11 17
7. 19 13 19
8. 21 15 20

3
 PART III:(4.5 pts)
Short answer
1. Assume you were tasked with conducting research on measuring the satisfaction level of Arsi
University students regarding the library:
A. What would be your dependent variable? (1.5pts)
B. How would you define your dependent variable?(1.5pts)
C. What econometric model would be appropriate for the analysis?(1.5pts)