Scribd
Upload
2 views

Assignment 3

Uploaded by

liuzhe20030124
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
2 views

Assignment 3

Uploaded by

liuzhe20030124
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/ 5

Time Series Analysis

ASSIGNMENT THREE

This assignment accounts for 10% of the total course mark. (Remarks for each problem is
indicated at the end of the question. This will be translated to the final course grade
proportionally.)

Some problems need to be completed by R. Please include your code at the end of the
assignment as Appendix.

Please hand in the answers in class. Be sure to include your name and ID number.

Please hand in on time. Otherwise, there will be a 50% discount on your remark.

1
1, (5’)

2,(5’*3=15’)

3,(5’*2=10’)

2
4, (25’)
In GNP_UE_Data.xlsx you will find Time Series data on Unemployment and
Gross Nation al Product (GNP) growth for the US from 1948Q2 to 1987Q4.
Note that both time series are measured in terms of percentages.
(a)

with p lags. How many lags do you select? (5’)

(b) Plot the impulse response of unemployment to a 1% shock to unemployment.


Do not worry about constructing confidence intervals. In the long-run, is the level
of unemployment higher or lower in response to the shock? (5’)

(c) Plot the cumulated impulse response of GNP to a 1% shock to unemployment.


Do not worry about constructing confidence intervals. Over the long-run, is the
level of GNP higher or lower in response to the shock? (5’)

3
(d) Plot the cumulated impulse response of GNP to the two kinds of shock in the
Structural VAR model. You should have two different plots: One for each kind of
shock. Do not worry about confidence intervals. For each response function,
comment on both the short-run (first period after the shock) and the long-run
(thirty periods after the shock) effect of each kind of shock on the level of GNP in
your model. (10’)

5, (30’)
Consider the quarterly real GDP of United Kingdom, Canada, and the United
States from the first quarter of 1980 to the fourth quarter of 2017. The data are
available from the Federal Reserve Bank of St. Louis (FRED). (This is a very
useful data source. You need to download the data by yourself. Please download
the seasonally adjusted quarterly data.)

Let 𝒛! be the log GDP series.


(a) Use BIC to determine the order of a VAR(p) model for 𝒛! . Based on the
model you selected, is the series 𝒛! cointegrated at the 5% level? Why?
(5’)
(b) How many cointegrating vectors are there? Write down the cointegrating
vector, if any. (10’)
(c) Compute the cointegrated series 𝒘! if any. Perform univariate unit-root
test to confirm the stationarity of the components of 𝒘! . Draw your
conclusion at the 5% significance level. (5’)
(d) Build an ECM-VAR model for 𝒛! . Perform model checking and write
down the fitted model. (10’)

4
6,(5’*3=15’)

You might also like