ECS4863: Review and Statistics | Time Series Concepts | Demonstrate Tests for Unit Roots - Econometrics Assignment Help

Internal Code: 1AJBHE

Econometrics Assignment

This assignment deals with the following assessment criteria: - Review of econometrics and statistics - Time series concepts - Demonstrate tests for unit roots. Question 1:  1.1 The following statements are either true or false. In addition to stating whether the statement is true or false, provide an explanation of why this is the case. (5) (a) If there is no intercept in the regression model, the estimated ( ) i i u = uˆ will not sum to zero. (b) The p-value and the size of a test-statistic mean the same. (c) The t-test of significance requires that the sampling distributions of estimators 1 ?ˆ and 2 ? ˆ follow the normal distribution (d) If heteroscedasticity is present, the conventional t and F tests are invalid. (e) A significant Durbin – Watson d does not necessarily mean there is autocorrelation of the first order. 1.2 Hypothesis testing answers this question: Is a given finding compatible with a stated hypothesis or not? Explain how the use of confidence intervals and test of significance assist in answering this question. 1.3 Using the World Bank Data Online Source, extract data for Botswana’s Imports (IMP), GDP and the Consumer Price Index (CPI) for the period 1980 -2016. The steps on how to extract this data are available on myUnisa/additional resources/assignment data: Assignment 01_data_Guidelines: Consider the following model: (a) Estimate the parameters of this model using Botswana data. (b) Do you suspect that there is multicollinearity in the data? (c) Perform the following regressions. i. t A A GDPt ln IM ln = 1 + 2 ii. t B B CPIt ln IM ln = 1 + 2 iii. GDPt C C CPIt ln ln = 1 + 2 (d) Based on these regressions, what can you say about the nature of multicollinearity in the data? (2) GDPt CPIt ut ln IM = ?1 + ? 2 ln + ? 3 ln + Question 2:  2.1. Explain the use of correlograms in time series analysis (2) 2.2. Distinguish between: (4) (a) Dickey Fuller (DF) test. (b) Augmented Dickey-Fuller (ADF) tests 2.3 It is common practice to include the time or trend variable in a regression model: (a) Explain the difference between a deterministic and stochastic trend. (4) (b) Differentiate between a trend stationary process (TSP) and difference stationary process (DSP) (5) Question 3:  3.1 Using the Botswana data obtained in question 1.3, conduct unit root tests for the three variables; Imports (IM), GDP and Consumer Price Index (CPI). (12) Remember to generate the logs of all the relevant variables, prior to conducting the tests. Series Model ADF Lags ADF ? ? ? ? ? IM * Statistically significant at the 10% level ** Statistically significant at the 5% level *** Statistically significant at the 1% level 3.2 Based on your findings in 3.1, comment on the order of integration of the three variables.