Scribd
Upload
72 views8 pages

Assignment 5: For Sheet Granger Causality

1) The document discusses performing a Granger causality test to ascertain whether there is causality between spot and future prices. The results show that differenced future prices Granger cause differenced spot prices but not vice versa. 2) It also discusses testing for cointegration between exchange rates and the Sensex index. Unit root tests show both series are non-stationary. Johansen cointegration tests find zero cointegrating vectors, so the series are not cointegrated.

Uploaded by

akshay kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
72 views8 pages

Assignment 5: For Sheet Granger Causality

1) The document discusses performing a Granger causality test to ascertain whether there is causality between spot and future prices. The results show that differenced future prices Granger cause differenced spot prices but not vice versa. 2) It also discusses testing for cointegration between exchange rates and the Sensex index. Unit root tests show both series are non-stationary. Johansen cointegration tests find zero cointegrating vectors, so the series are not cointegrated.

Uploaded by

akshay kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

ASSIGNMENT 5

For sheet Granger Causality

Q 1. Ascertain whether there is Granger Causality from spot prices to future prices or future
prices to spot prices

If we see above descriptive statistics we see that mean is greater than median for both of the
series making the series positively skewed. If we see the p-value we see that the out series are
not normally distributed.
Both of the graphs show an upward trend and we see that the series is not normally distributed.
And graphs have both intercept and trend.
 If we see the result of unit root test of both series we see that the p-value is greater than
0.05 so we fail to reject the null hypothesis. Which means unit root problem exist and
series are not stationary.
 As both of the series are non-stationary, we have to take differenced series because for
granger causality we need stationary series. So we will make the differenced series of both
spot and future.
If we see the above result of granger causality we see that for dspot does not granger cause dfut
because for that p_value is greater than 0.05 and we cannot reject the null hypothesis.
But we see the other hypothesis, we see that dfut granger cause dspot as the p-value is less than
0.05 and we can reject the null hypothesis.

For sheet Co-integration

Ascertain whether exchange rate and Sensex are co-integrated. Interpret the results.

As we see in the descriptive statistics mean and median don’t have much of the difference. For
closing price median is greater than the mean and for the US_dollar mean is greater than the
median. Skewness of both the series is positive.p-value of both is less than 0.05. Making both the
series not normally distributed.
Both of the graph shows an upward trend and have both trend and intercept. But they are not
stationary as we see the graph because the graph is not reverting around mean.
For both the series we have p-value greater than 0.05 making the series have unit root Problem
and non-stationary.
We will estimate the equation and save the residuals in a new variable name error and Perform
unit root on it to check the co-integration.
As we see there is unit root in error as well so we say that this series is non stationary and both
series is not co-integrated. We will perform another test to check co-integration test i.e Johansen
co-integration test.
Johansen co-integration test
Lag length interval is decided by lag length criteria: (1 5)

The Null Hypothesis in Trace is there are r co-integrating vector and alternate hypothesis is that
n>r co-integrating vectors.
INTERPRETATION
 If we see trace values for none means H0:0 co-integrating vectors, on the bases of p-value
we will not reject the null hypothesis so there is zero co-integration vectors. So, we
conclude that there is no cointegration between closing_price and us_dollar. Even if we
check from the Eigenvalue we get the same results.

You might also like