COINTEGRATION

Multivariate Unit Root

Processes
Generally we cannot reject the null
hypothesis, that many time series have unit
roots. For example,log consumption and log
output are both non-stationary, but log
consumption log output is stationary. This
situation is called cointegration. The
practical problem is that when we have
cointegration, asymptotics change
completely. Furthermore, we really do not
have enough data to defnitively tell
whether or not we have cointegrated series.
2

Multivariate Unit Root

Processes
In a univariate nonstationary time
series Yt is said to be integrated of order
d, I(d), if its (d1)th difference is
nonstationary but d-th difference is
stationary.
If Yt is nonstationary but Yt=(1B)Yt is
stationary, then Yt is integrated of order
1.
Yt~I(1) but Yt~I(0)
3

Multivariate Unit Root

Processes
In many time series, integrated processes
are considered together and they form
equilibrium relationships.
Short-term and long-term interest rates
Income and consumption

These leads to the concept of

cointegration.
The idea behind the cointegration is that
although multivariate time series is
integrated, certain linear transformations
of the time series may be stationary.
4

Granger Causality Tests

According to Granger, causality can be further
sub-divided into long-run and short-run causality.
This requires the use of error correction models or
VECMs, depending on the approach for
determining causality.
Long-run causality is determined by the error
correction term, whereby if it is signifcant, then it
indicates evidence of long run causality from the
explanatory variable to the dependent variable.
Short-run causality is determined as before, with a
test on the joint signifcance of the lagged
explanatory variables, using an F-test or Wald
test.
5

Granger Causality Tests

Before the ECM can be formed, there frst
has to be evidence of cointegration, given
that cointegration implies a signifcant error
correction term, cointegration can be viewed
as an indirect test of long-run causality.
It is possible to have evidence of long-run
causality, but not short-run causality and
vice versa.
In multivariate causality tests, the testing of
long-run causality between two variables is
more problematic, as it is impossible to tell
which explanatory variable is causing the
causality through the error correction term.
6

SPURIOUS REGRESSION
If we regress a y series with unit root on regressors
who also have unit roots the usual t tests on
regression coefficients show statistically signifcant
regressions, even if in reality it is not so.
The Spurious Regression Problem can appear with
I(0) series (see Granger, Hyung and Jeon (1998)).
This is telling us that the problem is generated by
using WRONG CRITICAL VALUES!!!!
In a Spurious Regression the errors would be
correlated and the standard t-statistic will be
wrongly calculated because the variance of the
errors is not consistently estimated. In the I(0) case
the solution is:

t t - distribution , where (long - run variance of )1/2

SPURIOUS REGRESSION
How do we detect a Spurious Regression
(between I(1) series)?
Looking at the correlogram of the residuals and also
by testing for a unit root on them.
How do we convert a Spurious Regression into
a valid regression?
By taking differences.
Does this solve the SPR problem?
It solves the statistical problems but not the
economic interpretation of the regression. Think that
by taking differences we are loosing information and
also that it is not the same information contained in
a regression involving growth rates than in a
regression involved the levels of the variables.
8

SPURIOUS REGRESSION
Typical symptom: High R2, t-values, F-value, but low
DW
1. Egyptian infant mortality rate (Y), 1971-1990, annual
data, on Gross aggregate income of American farmers
(I) and Total Honduran money supply (M)
Y ^ = 179.9 - .2952 I - .0439 M, R2 = .918, DW = .4752, F = 95.17
(16.63) (-2.32) (-4.26) Corr = .8858, -.9113, -.9445
2. US Export Index (Y), 1960-1990, annual data, on
Australian males life expectancy (X)
Y ^ = -2943. + 45.7974 X, R2 = .916, DW = .3599, F = 315.2
(-16.70) (17.76)
Corr = .9570
9

SPURIOUS REGRESSION
3. US Defense Expenditure (Y), 1971-1990, annual data,
on Population of South African (X)
Y ^= -368.99 + .0179 X, R2 = .940, DW = .4069, F = 280.69
(-11.34) (16.75) Corr = .9694
4. Total Crime Rates in the US (Y), 1971-1991, annual data,
on Life expectancy of South Africa (X)
Y ^= -24569 + 628.9 X, R2 = .811, DW = .5061, F = 81.72
(-6.03) (9.04)
Corr = .9008
5. Population of South Africa (Y), 1971-1990, annual data,
on Total R&D expenditure in the US (X)
Y ^= 21698.7 + 111.58 X, R2 = .974, DW = .3037, F = 696.96
(59.44)
(26.40) Corr = .9873
10

SPURIOUS REGRESSION
Does it make sense a regression between two
I(1) variables?
Yes if the regression errors are I(0).
Can this be possible?
The same question asked David Hendry to Clive
Granger time ago. Clive answered NO WAY!!!!! but
he also said that he would think about. In the plane
trip back home to San Diego, Clive thought about it
and concluded that YES IT IS POSSIBLE. It is possible
when both variables share the same source of the
I(1)ness (co-I(1)), when both variables move
together in the long-run (co-move), ... when both
variables are COINTEGRATED!
11

COINTEGRATION
An mx1 vector time series Yt is said to
be cointegrated of order (d, b), CI(d,b)
where 0<bd, if each of its component
series Yit is I(d) but some linear
combination of the series Yt is I(db)
for some nonzero constant vector .
is the cointegrating vector or the
long run parameter and it is not unique.
The most common case is d=b=1.
12

COINTEGRATION
More generally, if the mx1 vector series Yt
contains more than two components, each
being I(1), then there may exist k (<m) linearly
independent 1xm vectors 1, 2,, k, such
that Yt is a nonstationary kx1 vector process
where

1 , , k

is a kxm cointegrating matrix.

The number of linearly independent
cointegrating vectors is called the
cointegrating rank.
Yt is cointegrated of rank k.
13

EXAMPLE
Consider the following system of processes

x1t 1 x2t 2 x3t a1t

x2t 3 x3t a2t

x3t x3,t 1 a3t

where the three error terms are

uncorrelated white noise processes. Clearly,
all those three processes are individually
I(1). Let yt=(x1t,x2t,x3t) and =(1,1,2), then
yt=a1t. which is a I(0) process. Another
cointegrating relationship is between x2t and
x3t. So, we can let *= (0, 1,3), then *yt = a2t
is also I(0).
14

VAR with Cointegration

Let Yt be mx1. Suppose we estimate
VAR(p) Yt 1Yt 1 pYt p at

Yt B Yt 1 at .

or
Let say we have a unit root. Then, we
*
can write
B 1 1 B B
This is like a multivariate version of the
augmented Dickey-p Fuller test

Yt Yt 1 Yt i at .
i 1

15

VAR with Cointegration

Rearranging the equation

Yt 1 1 Yt 1 B Yt 1 at .

where Rank( (1)I)<m. There are two cases:

(1)= I the n we have m independent unit
roots, so there is no cointegration, and we
should run the VAR in differences.
0<Rank( (1)I)=k<m, then we can write (1)I
= where and are mxk. The equation
becomes:

Ytavector
Yt 1error
correction
B Yt 1 amodel
t.
This is called
(VECM).
*

16

VAR with Cointegration

Note that if you run OLS in differences, then the
modeled is misspecifed and the results will be
biased. What can you do?
(a)If you know the location of the unit roots and
cointegration relations, then you can run the
VECM by doing OLS of Yt on lags of Y and Yt1.
(b)If you know nothing, then you can either (i) run
OLS in levels, or (ii) test (many times) to
estimate cointegrating relations, and run VECM.
The problem with this approach is that you are
testing many times and you are estimating
cointegrating relationships. This leads to poor
fnite sample properties.
17

Residual Based Tests of the

Null of No Cointegration
Procedures designed to distinguish a system
without cointegration from a system with at
least one cointegrating relationship; they do
not estimate the number of cointegrating
vectors (the k). Tests are conditional on a
pretest for unit roots in each of the variables.
When the cointegration vector is known:
construct the hypothesized linear
combination that is stationary, treat it as
data, and apply a Dickey-Fuller unit root test
to that linear combination. The null
hypothesis is that there is a unit root, or no
cointegration.
18

Residual Based Tests of the

Null of No Cointegration
When the cointegration vector is not known:
Assume that, if there exists a cointegrating
relation, the coefficient on Y1t is nonzero, allowing
us to express the static regression equation as

Y2t ut
Y

1t
You can apply a unit root test to the estimated OLS
residual from estimation of the above equation,
but

Include a constant in the static regression if the

alternative allows for a nonzero mean in ut
Include a trend in the static regression if the
alternative is stochastic cointegration, i.e., a nonzero
trend for AYt.
19

Residual Based Tests of the

Null of No Cointegration
The frst step in testing cointegration
is to test the null hypothesis of a unit
root in each component series Yit
individually using the univariate unit
root tests.
If the hypothesis is rejected, then the
next step is to test cointegration
among the components, i.e., to test
whether Yt is stationary.
20

Residual Based Tests of the

Null of No Cointegration
In practice, the cointegration vector is
unknown. One way to test the
existence of cointegration is the
regression method (Engle&Granger,
1986, 1987).
If Yt=(Y1t,Y2t,,Ymt) is cointegrated, Yt is
stationary where =(1, 2,, m). Then,
(1/1) is also a cointegrated vector
where 10.
21

Residual Based Tests of the

Null of No Cointegration
Consider the regression model for Y1t
Y1t 1Y2t m1Ymt t
and check whether t is I(1) or I(0).
If t~I(1), then Yt is not cointegrated.
If t~I(0), then Yt is cointegrated with a
normalizing cointegrating vector
=(1,1,, m1) .
22

Residual Based Tests of the

Null of No Cointegration
In testing the error series for
nonstationary,
1,1 , ,m1 .
Calculate the OLS estimate
t
Use the residual series
for the test
asympt .
using
ADF or PP .
i ~ the
t standard
distribution

if t~I(0).
p 1the model
H0: =1 vs H1: <1 for

t t 1 j t j at
j 1

p 1
H0: =0 vs H1: <1 for
the model

t t 1 j t j at
j 1

23

Residual Based Tests of the

Null of No Cointegration
t-statistic:

T
s

The critical values are obtained by simulation

(Engle&Granger, 1987).
Level of significance 1% 5%
p=1
4.07
3.37
p>1
3.73
3.17
If T<Critical Value, reject H0Cointegration
exists.
24

The Johansen Trace and

Maximal Eigenvalue Tests
To test whether the variables are
cointegrated or not, one of the wellknown tests is the Johansen trace test.
The Johansen test is used to test for the
existence of cointegration and is based
on the estimation of the ECM by the
maximum likelihood, under various
assumptions about the trend or
intercepting parameters, and the number
k of cointegrating vectors, and then
conducting likelihood ratio tests.
25

The Johansen Trace and

Maximal Eigenvalue Tests
Assuming that the ECM errors are independent Nm[0, ]
distribution, and given the cointegrating restrictions on
the trend or intercept parameters, the maximum
likelihood Lmax(k) is a function of the cointegration rank
k.
The trace test is based on the log-likelihood ratio
ln[Lmax(k)/Lmax(k)], and is conducted sequentially for
k = m-1,...,1,0. The name comes from the fact that the
test statistics involved are the trace (the sum of the
diagonal elements) of a diagonal matrix of generalized
eigenvalues. This test examines the null hypothesis
that the cointegration rank is less than or equal to k,
against the alternative that the cointegration rank is
greater than k. If the trace is greater than the critical
value for a certain rank, then the null hypothesis that
the cointegration rank is equal to k is rejected.
26

The Johansen Trace and

Maximal Eigenvalue Tests
Consider a non-stationary cointegrated
VAR(p) model
( I 1B ... p Bp ) xt at
where at are normally distributed with
mean 0 and covariance matrix . In a
series of influential papers, Johansen
(1988, 1991), and Johansen and Juselius
(1990) proposed practical full maximum
likelihood estimation and testing
approaches based on the error correction
representation (ECM).
27

The Johansen Trace and

Maximal Eigenvalue Tests
Consider the ECM p1
x t 0 d t

x
j

t j

xt p at

j 1

where xt xt xt 1
,dt is a vector of
deterministic variables, such as constant
and seasonal dummy variables,
j I 1 L j , j = 1,L
are mm, A ,A and are mk
parameter matrices, the are i.i.d. Nm(0, )
errors, and
I B
det(
) has all of its roots outside the
unit circle.

, p-1

p 1

j 1

28

The Johansen Trace and

Maximal Eigenvalue Tests
This ECM is based on the Engle-Granger (1987)
error correction representation theorem for
cointegrated systems, and the asymptotic
inference involved is related to the work of Sims,
Stock, and Watson (1990).
By step-wise concentrating all the parameter
matrices in the likelihood function out except for
the matrix A, Johansen shows that the maximum
likelihood estimator of A can be derived as the
solution of a generalized eigenvalue problem.
Likelihood ratio tests of hypotheses about the
number of cointegrating vectors can then be based
on these eigenvalues. Moreover, Johansen (1988)
also proposes likelihood ratio tests for linear
restrictions on these cointegrating vectors.
29

The Johansen Trace and

Maximal Eigenvalue Tests
The Johansen test for the existence of cointegration is
based on the estimation of the above ECM by the
maximum likelihood and is used to test the
H 0hypothesis
: Rank k
, where k is less than m. This formulation
shows that I(1) models form nested sequence models

H 0 H k H m

where H(m) is the unrestricted VAR model or I(0)

model, and H(0) corresponds to the restriction =0,
A
which is the VAR model for indifferences.
Since
, it is equivalent to test that A and are of full
column rank k, the number of independent
cointegrating vectors that forms the matrix A. The
test has been named the Johansen trace test because
the likelihood ratio test statistic is the trace of a
diagonal matrix of generalized eigenvalues from .
30

The Johansen Trace and

Maximal Eigenvalue Tests
Sequential tests:
i. H0: k=0,
cannot be rejected stop
(at most zero coint)
rejected next test
ii. H0: k<=1,
cannot be rejected
stopk=1
(at most one coint)
rejected next test
iii. H0: k2,
cannot be rejected
stopk=2
(at most two coint)
rejected next test
31

The Johansen Trace and

Maximal Eigenvalue Tests
(i) Rank k = m: all variables in x are I(0), not an
interesting case to start with.
(ii) Rank k = 0: there are no linear combinations
of x that are I(0), no cointegration exists, and
is full of zeros. Model on differenced series
(iii) Rank k (m-1): up to (m-1) cointegration
relationships xt-k.
i.e. k (m-1) rows of form k linearly
independent combinations of variables in x,
each of which is I(0); alternatively (m-k)
nonstationary vectors forming I(1) stochastic
trends.
32

The Johansen Trace and

Maximal Eigenvalue Tests
Under some regularity conditions, we
can write the cointegrated process
as an Error Correction Model (ECM):
xt 1xt 1 ... p 1xt p 1 xt p at

where is the difference operator ,

the at's are i.i.d. N(0, ).

33

The Johansen Trace and

Maximal Eigenvalue Tests
We can write this ECM as

Z 0 t Z1t Z pt at
where Z x Z, (x ,..., x ) Z ,x
,,..., )

1
p 1
0t
t
pt
t p
1t
t 1
t p 1
The likelihood ratio statistic for hypothesis
is given by
H 0 : A

2
ln

n
ln
1

i
denotes the eigenvalues
of
m

where
and arei ordered by

i k 1

1
S p 0 S00
S0 p wrt S pp

1 m 0.
34

The Johansen Trace and

Maximal Eigenvalue Tests
Where

1
11

Sij M ij M i1M M ij
1

M ij n Z it Z jt ; i , j 0 ,1, p .
t 1

If the test statistics are greater than

the critical value for rank k, then the
null hypothesis that the cointegration
rank is equal to k is rejected.
35

The Johansen Trace and

Maximal Eigenvalue Tests
The statistic ln has the following
limiting distribution which can be
expressed in terms of a mk dimensional
1 1
Brownian motion
as
1
1

tr dY Y YY dt
Y
d
Y

The percentiles of the asymptotic

distribution for the trace statistic are
tabulated in Johansen (1988, Table 1)
using simulation analysis.
36

The Johansen Trace and

Maximal Eigenvalue Tests
An alternative LR statistic, given by
2 ln n ln1 k 1

and called the maximal eigenvalue

statistic, examines the null hypothesis
of k cointegrating vectors versus the
alternative k+1 cointegrating vectors.
The asymptotic distribution of this
statistic is given by the maximum
eigenvalue of
the stochastic
matrix
in
1 1
1
1

dY Y
0

YY dt
0

Y dY

37

Analysis of U.S.
Economic Variables
(From SAS Online Doc)

Consider the following fourdimensional system of U.S. economic

variables. Quarterly data for the
years 1954 to 1987 are used
(Ltkepohl 1993, Table E.3.). The
following statements plot the series
and proceed with the VARMAX
procedure.
38

SAS Code
symbol1 v=none height=1 c=black;
symbol2 v=none height=1 c=black;
title 'Analysis of U.S. Economic Variables';
data us_money;
date=intnx( 'qtr', '01jan54'd, _n_-1 );
format date yyq. ;
input y1 y2 y3 y4 @@;
y1=log(y1);
y2=log(y2);
label y1='log(real money stock M1)' y2='log(GNP in bil.
of 1982 dollars)' y3='Discount rate on 91-day T-bills'
y4='Yield on 20-year Treasury bonds';
datalines;
... data lines omitted ... ;
legend1 across=1 frame label=none;
39

SAS Code (Contd.)

proc gplot data=us_money;
symbol1 i = join l = 1;
symbol2 i = join l = 2;
axis2 label = (a=-90 r=90 " ");
plot y1 * date = 1 y2 * date = 2 / overlay vaxis=axis2 legend=legend1;
run;
proc gplot data=us_money;
symbol1 i = join l = 1;
symbol2 i = join l = 2;
axis2 label = (a=-90 r=90 " ");
plot y3 * date = 1 y4 * date = 2 / overlay vaxis=axis2 legend=legend1;
run;
proc varmax data=us_money;
id date interval=qtr;
model y1-y4 / p=2 lagmax=6 dftest print=(iarr(3))
cointtest=(johansen=(iorder=2)) ecm=(rank=1 normalize=y1); cointeg
rank=1 normalize=y1 exogeneity;
run;

40

SAS Output
This example performs the DickeyFuller test for stationarity, the
Johansen cointegrated test integrated
order 2, and the exogeneity test. The
VECM(2) fts the data. From the
outputs shown below, you can see
that the series has unit roots and is
cointegrated in rank 1 with integrated
order 1. The ftted VECM(2) is given as
41

SAS Output

42

SAS Output
Dickey-Fuller Unit Root Tests
Variable Type

Rho

Pr <
Rho

Tau

Pr < Tau

y1

Zero
Mean

0.05

0.6934

1.14

0.9343

Single
Mean

-2.97

0.6572

-0.76

0.8260

Trend

-5.91

0.7454

-1.34

0.8725

y2

Zero
Mean

0.13

0.7124

5.14

0.9999

Single
Mean

-0.43

0.9309

-0.79

0.8176

Trend

-9.21

0.4787

-2.16

0.5063

y3

Zero
Mean

-1.28

0.4255

-0.69

0.4182

Single
Mean

-8.86

0.1700

-2.27

0.1842

Trend

-18.97

0.0742

-2.86

0.1803

y4

Zero
Mean

0.40

0.7803

0.45

0.8100

Single
Mean

-2.79

0.6790

-1.29

0.6328

Trend

-12.12

0.2923

-2.33

0.4170

43

SAS Output
Cointegration Rank Test for I(2)
r\k-r-s
0

Trace
of I(1)

5% CV
of I(1)

55.9633

47.21

219.6239
89.21508 27.32609 20.6542
5

29.38

384.6090 214.3790 107.9378

37.02523
3
4
2

5% CV
I(2)

73.61779 22.13279

47.21000 29.38000 15.34000

2.6477

15.34

38.29435

0.0149

3.84

3.84000

44

SAS Output
Long-Run Parameter
Beta Estimates When
RANK=1

Adjustment Coefficient
Alpha Estimates When
RANK=1

Variable

Variable

y1

1.00000

y1

-0.01396

y2

-0.46458

y3

14.51619

y2

-0.02811

y4

-9.35520

y3

-0.00215

y4

0.00510

45

Diagnostic Checks
Schematic Representation of Cross Correlations
of Residuals
Variabl
0
e/Lag

y1

++..

....

++..

....

+...

..--

....

y2

++++ ....

....

....

....

....

....

y3

.+++

....

+.-.

..++

-...

....

....

y4

.+++

....

....

..+.

....

....

....

+is>2*stderror,-is<-2*stderror,.isbetween
Portmanteau Test for Cross Correlations
of Residuals
Up To Lag

DF

Chi-Square

Pr>ChiSq

16

53.90

<.0001

32

74.03

<.0001

48

103.08

<.0001

64

116.94

<.0001

46

Diagnostic Checks
Univariate Model ANOVA Diagnostics
Variable

Standard
R-Square Deviatio
n

F Value

Pr>F

y1

0.6754

0.00712

32.51

<.0001

y2

0.3070

0.00843

6.92

<.0001

y3

0.1328

0.00807

2.39

0.0196

y4
0.0831
0.00403
1.42
0.1963
Univariate Model White Noise Diagnostics
Variabl
e

Durbin
Watso
n

y1
y2
y3

Normality

ARCH

ChiSquare

Pr>C
hiSq

F Value

Pr>F

2.1341
8

7.19

0.0275

1.62

0.2053

2.0400
3

1.20

0.5483

1.23

0.2697

1.8689

253.76

<.000

1.78

0.1847

47

Diagnostic Checks
Univariate Model AR Diagnostics
AR1
Variabl
e
F Value Pr>F

AR2

AR3

AR4

F Value

Pr>F

F Value

Pr>F

F Value

Pr>F

y1

0.68

0.4126

2.98

0.0542

2.01

0.1154

2.48

0.0473

y2

0.05

0.8185

0.12

0.8842

0.41

0.7453

0.30

0.8762

y3

0.56

0.4547

2.86

0.0610

4.83

0.003
2

3.71

0.006
9

y4

0.01

0.9340

0.16

0.8559

1.21

0.3103

0.95

0.4358

48

Diagnostic Checks
Testing Weak Exogeneity of
Each Variables
Variable

DF

Chi-Square

Pr>ChiSq

y1

6.55

0.0105

y2

12.54

0.0004

y3

0.09

0.7695

y4

1.81

0.1786

Whether each variable is the weak exogeneity of other variables. The

variable y1 is not the weak exogeneity of other variables, y2, y3, and
y4; the variable y2 is not the weak exogeneity of other variables, y1,
y3, and y4.
If a variable can be taken as "given" without losing information for
the purpose of statistical inference, it call weak exogenous.
Weak exogeneityLong-run noncausality

49