(Answered) In this question, you must estimate a time series model for consumer prices in South Africausing…

Written by

in

In this question
In this question, you must estimate a time series model for consumer prices in South Africausing data in the Excel file ECS4863.xls . You are provided with the following data:
Variable names and descriptions:
SA_CPI = South African headline consumer price index (all urban areas)
EXCH= South African rand per euro
Rand = South African rand per US dollar
OIL = Brent crude oil in South African rand per barrel
M3 = South African money supply in million rands
EU_CPI = Euro area Harmonised consumer price index
US_CPI = United States of America consumer price index
NB, Log transform all the variables. L indicates the logarithmic function is used.
3.1 3.2
Use the data to calculate the annual consumer price inflation and annual South Africaper Euro exchange rate growth. [ N.B Calculate the month-on-same-month of theprevious year (i.e. 12 months) inflation and growth rate]. Plot both series in a scatterplotand comment on the relationship. Perform the Ganger causality test and interpret theresults. Find the correlation coefficient between the series and determine if it isstatistically significant (6)
Test the variables LOIL, LEXCH, and LEU_CPI for stationarity (transform all applicablevariables). Also comment on their respective orders of integration. Provide your resultsin the table below (please add rows where necessary): (9)
Variable Model Lags ADF teststatistic Conclusion
LOIL Trend &InterceptInterceptNone
LEU_CPI Trend&InterceptInterceptNone
LEXCH Trend &InterceptInterceptNone
Statistically significant at the: 10% level (*), 5% level (**), 1% level (***)
You can assume that all other variables are non-stationary, integrated of order I(1).
3.3 Test for possible cointegration between variables
(i) Estimate the following long-run cointegration equation using OLS. Copy and paste your EViews results window in your answer sheet.
(1)_ = 0 + 1 + 20 + 3_ + 43 + . ( 1)
(ii) What are your apriori expectations in terms of sign? (4)
(iii) Interpret the estimated coefficients in equation (1). (4)
(iv) Determine the hypothesis of complete exchange rate and euro area consumer pricepassthrough to the South African consumer price index, that is, 1 = 1 and 3 = 1 (4)
(v) Determine whether LM3 and LEU_CPI are redundant variables in equation (1). (4)
(vi) Determine whether LUS_CPI and LRAND are omitted variables in the model (4)
(vii) Generate the residual series for your long-run equation and determine if cointegrationexists between the variables in the long-run model. (3)
3.4 Construct a short-run (Error Correction) component for your model
_ = 0 + 1_1 + 20 + 301 + 4_ + 531 +61 + 71 + . (2)
(i) Estimate the short-run cointegration equation. Copy and paste your EViews resultswindow in your answer sheet.
(ii) Interpret the coefficients 1 to 7 of the short-run model. (7)
(iii) Perform the required diagnostic and stability tests on the residuals of the Error CorrectionModel given by equation (2). Interpret the test results and make conclusions. (8)
a) Jarque-Bera
b) Breusch Godfrey LM TEST
c) Glejser test
d) Ramsey RESET

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *