Mohamed Khidher University

Faculty of economics, Commercial Specialty: International Commerce & Finance

and Management Sciences Module: Advanced Econometric
Department of commerce Academic year 2023/2024

Exercise series N°4 solution

Exercise 1:

1. Which of the following statements about the Augmented Dickey-Fuller (ADF) test is true?
a) It is used to test for the presence of cointegration.
b) It is used to test for stationarity in a time series.
c) It is used to test for the presence of unit root.
d) Both b & c.

2. What is the null hypothesis in an Augmented Dickey-Fuller (ADF) test?

a) The time series is stationary.
b) The time series has a unit root.
c) The time series has no unit root test.
d) The time series is cointegrated.

3. How do you interpret the p-value obtained from the ADF test?

a) If the p-value is less than the significance level (e.g., 0.05), we reject the null hypothesis of
non-stationarity.
b) If the p-value is greater than the significance level, we reject the null hypothesis of stationarity.
c) The p-value indicates the strength of the stationarity in the time series.
d) The p-value represents the test statistic divided by the number of observations.
4. What do the critical values in the ADF test indicate?
a) They represent the upper and lower bounds for the test statistic beyond which we reject the null
hypothesis.
b) They represent the significance level at which the null hypothesis is rejected.
c) They measure the autocorrelation in the time series data.
d) They quantify the strength of the stationarity in the time series.
5. Which of the following statements about unit root tests is true?

a) A unit root indicates that a time series is stationary.

b) A unit root indicates that a time series is non-stationary.
c) Unit root tests are used to test for the presence of trends in a time series.
d) A significant p-value in a unit root test implies stationarity.

6. Which test is commonly used to detect the presence of a unit root in a time series?
A) Engle-Granger test
B) Augmented Dickey-Fuller (ADF) test
 C) Johansen test
D) Granger causality test
7. In the context of cointegration, what does it mean if the Johansen’s test statistic is significant?
a) The variables are not cointegrated.
b) The variables are cointegrated.
c) The variables has a long run relationship.
d) The variables are not stationary.

8. In the context of cointegration, what does it mean if the p-value of the Johansen’s test is less than
the significance level (e.g., 0.05)?
a) Reject the null hypothesis; the variables are not cointegrated.
b) Fail to reject the null hypothesis; the variables are cointegrated.
c) Reject the null hypothesis; the variables are cointegrated.
d) Fail to reject the null hypothesis; the variables are not cointegrated.

9. Cointegration between two time series means that:

a) Both series are non-stationary.

b) Both series are stationary.
c) There is a long-term relationship between the two series.
d) The two series are perfectly correlated.

10. What is the purpose of the Johansen cointegration test?

a) To determine the causality between time series variables.

b) To assess the presence of long-term relationships among multiple time series variables.
c) To measure the autocorrelation in the time series data.
d) To determine the seasonality in time series data.

11. How do you interpret the eigenvalue obtained from the Johansen cointegration test?

a) It represents the number of cointegrating equations.

b) It quantifies the strength of the cointegration relationship.
c) It measures the autocorrelation in the time series data.
d) It indicates the significance of the test statistic.

12. What does the trace statistic in the Johansen cointegration test indicate?

a) It represents the number of cointegrating equations.

b) It quantifies the strength of the cointegration relationship.
c) It measures the autocorrelation in the time series data.
d) It assesses the overall significance of the test.

13. How do you interpret the critical values in the Johansen cointegration test?

a) They represent the upper and lower bounds for the test statistic beyond which we reject the null
hypothesis.
 b) They represent the significance level at which the null hypothesis is rejected.
c) They measure the autocorrelation in the time series data.
d) They quantify the strength of the cointegration relationship.

14. In the context of cointegration tests, what does it mean if the trace statistic exceeds the critical
value?

a) The null hypothesis of no cointegration is rejected.

b) The null hypothesis of cointegration is rejected.
c) The time series variables are stationary.
d) The time series variables are non-stationary.

15. The OLS estimator is considered efficient and unbiased when:

a) The errors are heteroscedastic
b) The errors are autocorrelated
c) The errors are normally distributed
d) The Gauss-Markov assumptions are satisfied

16. Which of the following statements about Ordinary Least Squares (OLS) regression is correct?

a) OLS always produces unbiased estimates of regression coefficients.

b) OLS minimizes the sum of squared residuals.
d) OLS assumes that the residuals are normally distributed.

17. If the coefficient of determination (R-squared) of a linear regression model is 0.75, what
percentage of the variation in the dependent variable is explained by the independent variables?
a) 25%
b) 75%
c) 100%
d) 50%
Exercise 2:

Suppose you have conducted an Augmented Dickey-Fuller (ADF) test to assess the stationarity
of a time series data. After running the test, you obtain the following results table:

Lag length 3
Obs. 18 t-statistic Prob.*
Augmented dikey-Fuller test statistic -0.742941 0.8096
Test critical values 1% level -3.886751
5% level -3.052169
10% level -2.666593

Based on the given results, answer the following questions:

1. What is the test statistic obtained from the ADF test?
2. What is the p-value associated with the test?
 3. How many lags were used in the test?
4. How many observations were included in the analysis?
5. What are the critical values at the 1%, 5%, and 10% significance levels?

Answers :
1. The test statistic obtained from the ADF test is -0.742941.
2. The p-value associated with the test is 0.8096.
3. The number of lags used in the test is 3.
4. The number of observations included in the analysis is 18.
5. The critical values at the 1%, 5%, and 10% significance levels are:
• 1% level: -3.886751
• 5% level: -3.052169
• 10% level: -2.666593

Exercise 3:

Suppose you have conducted a Johansen cointegration test to assess the presence of cointegration
among two time series variables. After running the test, you obtain the following results table:
Johansen Cointegration Test Results
====================================
Hypothesized No. of Cointegrating Eqn 1
Eigenvalue 0.150
Trace Statistic 18.267
Critical Value (10%) 13.429
Critical Value (5%) 15.494
Critical Value (1%) 20.261

Based on the given results, answer the following questions:

6. What is the number of hypothesized cointegrating equations in the test?
7. What is the eigenvalue obtained from the cointegration test?
8. What is the trace statistic computed from the test?
9. What are the critical values at the 10%, 5%, and 1% significance levels?

Answers :
6. The number of hypothesized cointegrating equations in the test is 1.
7. The eigenvalue obtained from the cointegration test is 0.150.
8. The trace statistic computed from the test is 18.267.
9. The critical values at the 10%, 5%, and 1% significance levels are:
• Critical Value (10%): 13.429
• Critical Value (5%): 15.494
• Critical Value (1%): 20.261