1

1
Roy Batchelor 2000 EVIEWS Tutorial 1
EVI EWS tutorial:
Cointegration and error correction
Professor Roy Batchelor
City University Business School, London
& ESCP, Paris
Roy Batchelor 2000 EVIEWS Tutorial 2
EVI EWS
r On the City University system, EVIEWS 3.1 is in
Start/ Programs/ Departmental Software/CUBS
r Analysing stationarity in a single variable using VIEW
r Analysing cointegration among a group of variables
r Estimating an ECM model
r Estimating a VAR-ECM model
2
2
Roy Batchelor 2000 EVIEWS Tutorial 3
The FT500M workfile
Roy Batchelor 2000 EVIEWS Tutorial 4
Data transformation
r Generate a series for the natural log of the FT500 index (lft500)
r Test for stationarity in
the level of this series
the first difference of this series (dlft500)
r Results show that lft500 is an I(1) variable
3
3
Roy Batchelor 2000 EVIEWS Tutorial 5
Generate ln(FT500)
Roy Batchelor 2000 EVIEWS Tutorial 6
Augmented Dickey-Fuller (ADF) Test
4
4
Roy Batchelor 2000 EVIEWS Tutorial 7
ADF results: level
The hypothesis that
lft500 has a unit root
cannot be rejected
The hypothesis that
lft500 has a unit root
cannot be rejected
Roy Batchelor 2000 EVIEWS Tutorial 8
ADF test results: first difference
The hypothesis that
the first difference of
lft500 has a unit root
can be rejected.
So lft500 is I(1)
The hypothesis that
the first difference of
lft500 has a unit root
can be rejected.
So lft500 is I(1)
5
5
Roy Batchelor 2000 EVIEWS Tutorial 9
Cointegration: two variables
r The variables lft500 (log of stock index) and ldiv (log of
dividends per share) are both I(1)
r We can test whether they are cointegrated
that is, whether a linear function of these is I(0)
An example of a linear function is
lft500
t
= a
0
+ a
1
ldiv
t
+ u
t
when u
t
= [lft500
t
- a
0
- a
1
ldiv] might be I(0)
r The expression in brackets [] is called the cointegrating vector,
which has normalised coefficients [ 1, -a
0
, -a
1
]
Roy Batchelor 2000 EVIEWS Tutorial 10
Form new group ...
6
6
Roy Batchelor 2000 EVIEWS Tutorial 11
Common trends?
Roy Batchelor 2000 EVIEWS Tutorial 12
Engle-Granger: first stage regression
Dont worry
about this...
Dont worry
about this...
7
7
Roy Batchelor 2000 EVIEWS Tutorial 13
Save first-stage residuals (u
t
= RES)
Roy Batchelor 2000 EVIEWS Tutorial 14
Engle-Granger:stage two (ECM) regression
About 7% of
disequilibrium
corrected each
month
About 7% of
disequilibrium
corrected each
month
8
8
Roy Batchelor 2000 EVIEWS Tutorial 15
General model: stage one (I (1) variables)
Roy Batchelor 2000 EVIEWS Tutorial 16
General model: stage two
9
9
Roy Batchelor 2000 EVIEWS Tutorial 17
Specific model:stage two
Roy Batchelor 2000 EVIEWS Tutorial 18
1-month ahead forecasts of lft500 from first
stage regression
10
10
Roy Batchelor 2000 EVIEWS Tutorial 19
1-month ahead forecasts of dlft500 from
the second stage ECM
Roy Batchelor 2000 EVIEWS Tutorial 20
1-month ahead changes in lft500:
actual v. forecast
11
11
Roy Batchelor 2000 EVIEWS Tutorial 21
J ohansen method: make group of
associated I (1) variables (lft500, ldiv)
Roy Batchelor 2000 EVIEWS Tutorial 22
Set up J ohansen procedure
12
12
Roy Batchelor 2000 EVIEWS Tutorial 23
J ohansen test for cointegrating vector(s)
Roy Batchelor 2000 EVIEWS Tutorial 24
Cointegrating vector (cf. First stage
regression)
13
13
Roy Batchelor 2000 EVIEWS Tutorial 25
Set up VAR-ECM
Roy Batchelor 2000 EVIEWS Tutorial 26
Cointegrating vector of both endogenous
I (1) variables
14
14
Roy Batchelor 2000 EVIEWS Tutorial 27
VAR-ECM-X models for both endogenous
variables
About 10% of
disequilibrium
corrected each month
by changes in stock
index lft500
About 10% of
disequilibrium
corrected each month
by changes in stock
index lft500
About 2% of
disequilibrium
corrected each month
by changes in dividends
ldiv
About 2% of
disequilibrium
corrected each month
by changes in dividends
ldiv
Exogenous I(0)
variables
affecting stock
index and
dividends
Exogenous I(0)
variables
affecting stock
index and
dividends
Roy Batchelor 2000 EVIEWS Tutorial 28
Forecasting: make VAR-ECM model
15
15
Roy Batchelor 2000 EVIEWS Tutorial 29
Dynamic forecasting: 1 year ahead
Roy Batchelor 2000 EVIEWS Tutorial 30
Stock index and dividend forecasts, 1996
16
16
Roy Batchelor 2000 EVIEWS Tutorial 31
Updated model (1975-98)
Roy Batchelor 2000 EVIEWS Tutorial 32
Forecasts for 1999-2000: a Crash coming?