Chapter 8

Modelling long-run relationship in finance

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 1

 Stationarity and Unit Root Testing
Why do we need to test for Non-Stationarity?

• A stationary series can be defined as one with a constant mean, constant

variance and constant autocovariances for each given lag.
• The stationarity )or otherwise( of a series can strongly influence its behaviour
and properties.

• For a stationary series, ‘shocks’ to the system will gradually die away. That is, a
shock during time t will have a smaller effect in time t + 1, a smaller effect still
in time t + 2, and so on.
• This can be contrasted with the case of non-stationary data, where the
persistence of shocks will always be infinite.

• The use of non-stationary data can lead to spurious regressions.

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 2

 Spurious regressions

Spurious regressions means if two variables are trending over time, a regression
of one on the other could have a high R2 even if the two are totally unrelated.
So if standard regression techniques are applied to non-stationary data, the result
could be a regression that ‘looks’ good under standard measures (significant
coefficient estimates and a high R2, but which is really valueless such a model
would be termed a ‘spurious regression’

• If the variables in the regression model are not stationary, then it can be proved
that the standard assumptions for asymptotic analysis will not be valid. In other
words, the usual “t-ratios” will not follow a t-distribution, so we cannot validly
undertake hypothesis tests about the regression parameters.

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 3

 Notes
if you’re analysing time series is that the existence of unit roots (series is not
stationary) can cause your analysis to have serious issues like:

Spurious regressions:
you could get high r-squared values even if the data is uncorrelated.

Errant behavior:
due to assumptions for analysis not being valid. For example, t-ratios will not follow
a t-distribution.

In statistics, a unit root test tests whether a time series variable is non-stationary and
possesses a unit root. The null hypothesis is generally defined as the presence of a
unit root and the alternative hypothesis is either stationarity, trend stationarity.

H0: series has a unit root (means series is Not stationary)

H1: series is a stationary
‘Introductory Econometrics for Finance’ © Chris Brooks 2013 4
 Two types of Non-Stationarity

Various definitions of non-stationarity exist. In this chapter, we are really

referring to the weak form or covariance stationarity
• There are two models which have been frequently used to characterise non-
stationarity: 1- the random walk model with drift:
yt =  + yt-1 + ut (1)

and the 2- trend-stationary process:

yt =  +  t + u t (2)

where ut is white noise disturbance term in both cases

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 5

 Detrending a Series: Using the Right Method

• Although trend-stationary and difference-stationary series are both “trending”

over time, the correct approach needs to be used in each case.

• If we first difference the trend-stationary series, it would “remove” the non-

stationarity, but at the expense on introducing an MA(1) structure into the
errors.

• Conversely if we try to detrend a series which has stochastic trend, then we

will not remove the non-stationarity.

• We will now concentrate on the stochastic non-stationarity model since

deterministic non-stationarity does not adequately describe most series in
economics or finance.
‘Introductory Econometrics for Finance’ © Chris Brooks 2013 6
 Definition of Non-Stationarity

• Consider again the simplest stochastic trend model:

yt = yt-1 + ut
or  yt = ut
• We can generalise this concept to consider the case where the series contains
more than one “unit root”. That is, we would need to apply the first difference
operator, , more than once to induce stationarity.

Definition
If a non-stationary series, yt must be differenced d times before it becomes
stationary, then it is said to be integrated of order d. We write yt I(d).
So if yt  I(d) then dyt I(0).
An I(0) series is a stationary series
An I(1) series contains one unit root,
e.g. yt = yt-1 + ut
‘Introductory Econometrics for Finance’ © Chris Brooks 2013 7
 Characteristics of I(0), I(1) and I(2) Series

• An I(2) series contains two unit roots and so would require differencing
twice to induce stationarity.

• The majority of economic and financial series contain a single unit root,
although some are stationary and consumer prices have been argued to
have 2 unit roots.

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 8

 How do we test for a unit root?

• The early and pioneering work on testing for a unit root in time series
was done by Dickey and Fuller (Dickey and Fuller 1979, Fuller 1976).
The basic objective of the test is to test the null hypothesis that  =1 in:
yt = yt-1 + ut
against the one-sided alternative  <1. So we have
H0: series contains a unit root
vs. H1: series is stationary.

• We usually use the regression:

yt = yt-1 + ut
so that a test of =1 is equivalent to a test of =0 (since -1=).

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 9

 Critical Values for the DF Test

Significance level 10% 5% 1%

C.V. for constant -2.57 -2.86 -3.43
but no trend
C.V. for constant -3.12 -3.41 -3.96
and trend
Table 4.1: Critical Values for DF and ADF Tests (Fuller,
1976, p373).

The null hypothesis of a unit root is rejected in favour of the stationary alternative
in each case if the test statistic is more negative than the critical value.

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 10

 Unit Root Tests with Structural Breaks

• The standard Dickey-Fuller-type unit root tests presented above do not perform
well if there are structural breaks in the series
• The tests have low power in such circumstances, and they fail to reject the unit
root null hypothesis when it is incorrect as the slope parameter in the regression
of yt on yt−1 is biased towards unity
• The larger the break and the smaller the sample, the lower the power of the test
• Unit root tests are also oversized in the presence of structural breaks

• Perron (1989) demonstrates that after allowing for structural breaks in the tests,
a whole raft of macroeconomic series may be stationary
• He argues that most economic time series are best characterised by broken trend
stationary processes, i.e. a deterministic trend but with a structural break.

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 11

 Application
Testing for unit roots in EViews

Import the dataset UKHP.XLS .

This example uses the monthly UK house price series There were a total of 269
monthly observations running from February 1991 (recall that the January
observation was ‘lost’ in constructing the lagged value) to May 2013 for the
percentage change in house price series DHP

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 12

• Open the raw house price series, ‘hp’ by clicking on the hp icon.
Next, click on the View button on the button bar above the
spreadsheet and then Unit Root Test... . You will then be
presented with a menu containing various options,

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 13

This will obviously perform
an augmented Dickey--Fuller
(ADF) test with up to 12 lags
of the dependent variable in a
regression equation on the
raw data series with a constant
but no trend in the test
equation

14
EViews presents a large number of options here -- for example,
instead of the Dickey--Fuller series, we could run the Phillips--Perron
or KPSS tests as described above.
Or, if we find that the levels of the series are nonstationary, we could
repeat the analysis on the first differences directly from this menu
rather than having to create the first differenced series separately.

We can also choose between various methods for determining the

optimum lag length in an augmented Dickey--Fuller test, with the
Schwarz criterion being the default.

15
The value of the test statistic and the relevant
critical values given the type of test equation
(e.g. whether there is a constant and/or trend
included) and sample size, are given in the first
panel of the output above.
Schwarz’s criterion has in this case chosen to
include 2 lags of the dependent variable in the
test regression.
Clearly, the test statistic (-0.47) is not more
negative than the critical value, so the null
hypothesis of a unit root in the house price
series cannot be rejected.
(so the series is Not stationary)
The remainder of the output presents the
estimation results. Since the dependent variable
in this regression is non-stationary, it is not
appropriate to examine the coefficient standard
errors or their t-ratios in the test regression.
16
Now repeat all of the above steps for
the first difference of the house price
series (use the ‘First Difference’ option
in the unit root testing window rather
than using the level of the dhp series)

In this case, the test statistic (-5.85) is

more negative than the critical value
and hence the null hypothesis of a unit
root in the first differences is
convincingly rejected.
So the series is stationary

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 17

 The end

‘Introductory Econometrics for Finance’ © Chris Brooks 2013 18