ECN5007 Applied Econometrics and Research Methods
TIME SERIES COURSEWORK 2025
This is the third and final assignment for ECN5007 and represents 20% of the final module grade.
It is an individual assessment.
There is one question which has multiple parts.
ATTEMPT ALL PARTS OF THE QUESTION.
There are 25 Marks in total.
The mark for each part of the question is indicated in bold.
The data file‘TS_CWK_25.xlsx’is provided within the time series assessment folder of the ECN5007 portal
EACH STUDENT HAS THEIR OWN DATASET. PLEASE REFER TO THE FILE ‘Dataset Key’ IN ORDER TO IDENTIFY YOUR PERSONAL DATASET. This file can be found within the time series assessment folder on the ECN5007 portal.
If you do not use the data set assigned to you, you will receive NO MARKS for the assessment.
Please make sure you put your STUDENT ID NUMBER and corresponding DATASET NUMBER on the cover sheet of your assessment submission.
MARKING CRITERIA
o Appropriate use of econometric methods
o Providing correct solutions the questions.
o Providing clear interpretations for your analyses 一 limited credit will be given for output without interpretation or comment.
There is no specific word limit for the piece. Most questions require two or three sentences of explanation.
You will need to use GRETL for this assignment 一 a copy is available from the ECN5007 DLE site.
Please present all GRETL output within your answer rather than as appendices.
Submit ONLINE to the ECN5007 DLE site on or before 3pm Thursday 1 May 2025
Late work will receive no marks.
Marks will be returned within 20 working days of receipt.
Please refer to the Module Handbook, in particular, Sections 9-16 for further information on for example, academic offences, extenuating circumstances etc.
ASSESSMENT QUESTION
The file‘TS_CWK_25.xlsx’shows quarterly data for a hypothetical country’s real GDP (£bn, GDP) and Unemployment rate (%, U) from 2000 Q1 to 2024 Q4. Both series have been seasonally adjusted. PLEASE MAKE SURE YOU USE THE DATA SET THAT HAS BEEN ASSIGNED TO YOU.
a. Make any transformation(s) necessary to the variables so that changes can be interpreted in percentage terms. State what transformation(s) you have made. (1 MARK)
b. Test the transformed variables for stationarity using the Augmented Dickey- Fuller (ADF) test with 4 AR lags and interpret the test results. Perform any further transformations and tests necessary to demonstrate that stationarity in both variables has been achieved. (3 MARKS)
(Note: you should retain any transformations made in part a and b throughout the remainder of question one)
c. Model GDP as a function of U using 4 distributed lags. Test back the lags of this model using the 5% significance level. (2 MARKS)
d. Interpret the value of R-squared and its statistical significance for the final model of part c. (1 MARK)
e. Interpret the individual model coefficients and their statistical significance for the final model in part c. (2 MARKS)
f. Show how you calculate the long-run elasticity of GDP with respect to U in the final model estimated in part c. Interpret the calculated value. (2 MARKS)
g. Test the final model in part c for first-order autocorrelation. Comment on whether the model is adequately specified. (1 MARK)
h. Estimate an Auto Regressive Distributed Lag (ARDL) model with one AR lag and two DL lag. Repeat steps fand g for this model i.e. show how you calculate the long-run elasticity and test for first order autocorrelation. Make sure you interpret the elasticity and the autocorrelation test. (3 MARKS)
i. Explain briefly what is meant by the term‘structural break’in the context of a time series econometric analysis. Test whether there is a structural break at any point in the model estimated in h. (2 MARKS)
j. Use the Vector Autoregressive (VAR) lag selection tool to determine the optimal lag structure for a VAR model between GDP and U, selecting 4 as the maximal lag structure. (Note - this tool is found under Model > Multivariate time series > VAR Lag selection) (1 MARK)
k. Based on this evidence, estimate an appropriate VAR. Comment on the nature of Granger Causality between the variables. Does the implied Granger Causality make‘economic sense’? Explain. (3 MARKS)
l. Use the VAR model estimated in j to forecast GDP and U for 2025 Q1 through to 2025 Q4.
YOU MUST SHOW THE WORKINGS OF YOUR FORECASTS CLEARLY TO RECEIVE CREDIT.
NOTE the forecasts of GDP and U should ultimately be presented in terms of their respective units in levels. (3 MARKS)
m. Considering the modelling approaches of parts c, h and j, which approach do you prefer and why? (1 MARK)