1

Cointegration and Error Correction Model

This part discusses a new theory for a regression with nonstationary unit root variables. In general, this should require a di¤erent treatment from a conventional regression with stationary variables, which has been covered so far. In particular, we focus on a class of the linear combination of the unit root processes known as cointegrated process.

1.1

Stylized Facts about Economic Time Series

Casual inspection of most economic time series data such as GNP and prices reveals that these series are non stationary. We can characterize some of the key feature of the various series as follows:

1. Most of the series contain a clear trend. In general, it is hard to distinguish between trend stationary and di¤erence stationary processes. 2. Some series seem to meander. For example, the pound/dollar exchange rate shows no particular tendency to increase or decrease. The pound seems to go through sustained periods of appreciation and then depreciation with no tendency to revert to a long-run mean. This type of random walk behavior is typical of unit root series.

1

3. Any shock to a series displays a high degree of persistence. For example, the UK industrial production plummeted in the late 1970s and not returning to its previous level until mid 80s. Overall the general consensus is at least empirically that most macro economic time series follow a unit root process.

4 Some series share co-movements with other series. For example, shortand long-term interest rate, though meandering individually, track each other quite closely maybe due to the underlying common economic forces. This phenomenon is called cointegration.

A note on notations: It is widely used that the unit root process is called an integrated of order 1 or for short I (1) process. On the other hand, a stationary process is called an I (0) process.1

1

In this regard we can de…ne I (d) process, and d is a number of di¤erencing to render the series stationary.

2

1.2

Spurious Regression

Suppose that two I (1) processes, yt and xt , are independently distributed. We now consider the following simple regression:

yt = xt + error:

Clearly, there should be no systematic relationship between y and x, and therefore, we should expect that an OLS estimate of

should be close to zero,

or insigni…cantly di¤erent from zero, at least as the sample size increases. But, as will be shown below, this is not the case. This phenomenon originated from Yule (1926) was called “a nonsense correlation.”

Example 1 There are some famous examples for spurious correlation. One is that of Yule (1926, Journal of the Royal Statistical Society), reporting a correlation of 0.95 between the proportion of Church of England marriages to all marriages and the mortality rate over the period 1866-1911. Yet another is the econometric example reported by Hendry (1980, Economica) between the price level and the cumulative rainfall in the UK.2

2

This relation proved resilient to many econometric diagnostic tests and was humorously advanced as a new theory of in‡ation.

3

As we have come to understand in recent years, it is commonality of (stochastic) trending mechanisms in data that often leads to these spurious relations. What makes the phenomenon dramatic is that it occurs even when the data are otherwise independent.

In a prototypical spurious regression the …tted coe¢ cients are statistically signi…cant when there is no true relationship between the dependent variable and the regressors. Using Monte Carlo simulations Granger and Newbold (1974, Journal of Econometrics ) showed this phenomenon. Phillips (1986, Journal of Econometrics ) derived an analytic proof. These results are summarized in the following theorem:

Theorem 1 (Spurious Regression) Suppose that y and x are independent I (1) variables generated respectively by

yt = yt

iid (0;

2
")

and et

+ "t ;

xt = xt

where "t

1

1

+ et ;

iid (0;

4

2
e ),

and "t and et are independent of

each other. Consider the regression,

(1)

y t = x t + ut :

Then, as T ! 1,
(a) The OLS estimator of

obtained from (1), denoted ^ , does not converge

to (true value of) zero.
(b) The t-statistic testing

= 0 in (1) diverges to

in…nity.

In sum, in the case of spurious regression, ^ takes any value randomly, and its t-statistic always indicates signi…cance of the estimate. Though a formal testing procedure will be needed to detect evidence of the spurious regression or cointegration (see below), one useful guideline is that we are likely to face with the spurious relation when we …nd a highly signi…cant t-ratio combined with a rather low value of R2 and a low value of the Durbin-Watson statistic.

1.3

Cointegration

Economic theory often suggests that certain subset of variables should be linked by a long-run equilibrium relationship. Although the variables under 5

consideration may drift away from equilibrium for a while, economic forces or government actions may be expected to restore equilibrium. Example 2 Consider the market for tomatoes in two parts of a country, the north and the south with prices pnt and pst respectively. If these prices are equal the market will be in equilibrium. So pnt = pst is called an attractor. If the prices are unequal it will be possible to make a pro…t by buying tomatoes in one region and selling them in the other. This trading mechanism will be inclined to equate prices again, raising prices in the buying region and lowering them in selling region.

When the concept of equilibrium is applied to I (1) variables, cointegration occurs; that is, cointegration is de…ned as a certain stationary linear combination of multiple I (1) variables.
Example 3 Consider the consumption spending model. Although both consumption and income exhibit a unit root, over the long run consumption tends to be a roughly constant proportion of income, so that the di¤erence between the log of consumption and log of income appears to be a stationary process. Example 4 Another well-known example is the theory of Purchasing Power Parity (PPP). This theory holds that apart from transportation costs, goods 6

should sell for the same e¤ective price in two countries. Let Pt denote the index of the price level in US (in dollars per good), Pt denote the price index for UK (in pounds per good), and St the rate of exchange between the currencies (in dollars per pound). Then the PPP holds that Pt = St Pt ; taking logarithm, pt = st + pt ; where pt = ln(Pt ); st = ln(St ); pt = ln(Pt ): In practice, errors in measuring prices, transportation costs and di¤erences in quality prevent PPP from holding exactly at every date t: A weaker version of the hypothesis is that the variable zt de…ned by zt = pt

st

pt is stationary,

even though the individual elements (pt ; st ; pt ) are all I (1). Cointegration brings with it two obvious econometric questions. The …rst is how to estimate the cointegrating parameters and the second is how to test whether two or more variables are cointegrated or spurious.

We …rst examine estimation of the cointegrating regression. Consider the simple time series regression,3

yt = x t + ut ;
3

(2)

The deterministic regressors such as intercept and a linear time trend can be easily accommodated in the regression without changing the results in what follows.

7

where xt is an I (1) variable given by

xt = xt

1

(3)

+ et :

Since xt is I (1), it follows that yt is I (1). But, for yt and xt to be cointegrated...

+1 +2 +6 -1 -1911 0 0.95 00 000 01 07 076 0x 1 1.1 1.2 1.3 1.3.1 1.4 10 11 12 13 14 15 16 17 18 1866 19 1926 1964 1970s 1974 1980 1986 1987 1990 1991 1999 1l 1st 1t 1x 2 2.1 2.2 2.2.1 2.2.2 2.2.3 2.2.4 2.3 20 21 22 23 24 25 26 27 28 29 2l 2t 3 30 31 32 33 34 35 36 37 3ext 4 5 54 545 6 60 61 6axx 6i 6i7 6q 6y 7 72 74 76 761 767 7e 8 80s 9 a0 a0zx a1 a1xx a1xz a1zx a1zz a2 a3 a4 ac acc accommod accomod account act action acwt add addit adequ adjust advanc aet ahead aic airj aj ak allow alon also altern although alway among amount analysi analyt announc anoth ap8 apart appear appli applic applicable.9 appreci approach approxim ar ardl ardl-bas arm ascertain associ assum assumpt assumption.1 asymptot ation attractor augment autoregress averag avt away axt axx axz ayt azx azz b back bank base basic becom behavior behind bivari bring built buy c c0 c0xx c0zx c0zz c1 c2 calcul call calli canc cannot cant captur carlo carri case casual cation caus causal cc ceint certain cet chang character choleski choos church cient cim cj ck class clear close co co-mov coe coin16 cointegr combin come common complic compon comput concept concern conclud conclus condit consensus consequ consid consider consist constant construct consumpt contain contemporan conveni convent converg correct correl correspond cost could countri cours covari cover criteria critic crucial cumul currenc current cwt cxx cxz czx czz d d0xx d0zx d0zz d1 d1xx d1xz d1zx d1zz data date de de-trend deal decid decomposit decreas degre denot depend depreci deriv describ desir detect determin determinist develop df di diagnost diagon dimens dimension direct discount discuss disequilibrium display distinguish distribu distribut disturb diverg dividend dollar dramat drift due durbin durbin-watson dynam e e1t e2t e7 easili ecm econom econometr econometrica economica ect ectiv ee egdf ekt element embed empir engl england ensur equal equat equi equilibrium equival erat erenc erence-stationari erent eroor error especi estim et et3 even everi evid exact examin exampl exchang exhibit exist exogen expect explain explanatori explicitly.7 express ext extend ezt f face fact failur fall famous far featur first focus follow forc forecast forecat form formal former formul found fraction function fundament furthermor futur fxt g gen general generat get give given gnp go good gordon govern granger guidelin h0 h1 hand hansen happen hard help henc hendri high hold howev humor hypothesi i.e i1 i2 ict idea ident iid iidn illustr im imp impli implicit import imprecis impuls impulse-respons impulse-resppons inclin includ inclus incom increas inde independ index india indic individu industri infer inform innov inpli insigni inspect instantan integr intercept interest interpret introduc intuit involv ir0 irj j j0 johansen joint journal jut jxt jyt k k-step k1 key know known l l2 la lack lag larg larger late lb lc ld lead least let level librium like limit linear link literatur ln log logarithm london long long-run long-term longer loretan low lower m m-th macro made main make mani map market marriag matric matrix may mayb mean meander measur mechan micro mid mislead model mont mortal motiv move movement much multicollinear multipl multipli must name nanc natur nd ne necessi ned need negat new newbold news next niti nition no-cointegr non non-standard non-zero nonsens nonstationari normal north notat note note3 notic null number numer o observ obtain obvious occur often ol one order orgin origin orthogon otherwis ouliari overal p p1 param paramet pariti part partial particular past path per percent perfect period persist pesaran phenomenon phillip pin pl plummet pnt polynomi popular possibl pound pound/dollar power ppp practic prece premis presenc present pretest prevent previous price prior priori pro proach problem procedur process process.1 produc product project proof properti proport prototyp prove provid pst pt purchas purpos pv q q1 qet qq qualiti question quit r2 rainfal rais ran random rank rate rather ratio re re-examin readili recal recent recurs reduc regard region regress regressor reject relat relationship reli remark render report repres represent requir rescal reserv residu residual-bas resili respect respond respons resppons restor restrict result return reveal revert review rhs root rough royal rst rst-di run sampl sargan save say sbc scale school second see seem select sell seri serial serious set sever share shin shock short short-run shortand show shown signi sim similar simpl simpli simul simultan sinc singl size small societi solv sometim south spe speci specifi spend spurious squar st stabil stabl standard start state static stationar stationari statist stem step stochast stock stock-pric strict studi styliz subsequ subset suggest sum summar suppos sustain system systemat t-ratio t-statist t-test t1 t17 t2 take tegrat tend tendenc ter term test th theorem theori therefor think though thought three three-step thus time time-seri time-vari tion tomato total track trade tradit traingular transform transitori transport treatment trend triangular true tted turn two two-step type typic u u3 uenc uk uk.2 uls uncertainti uncorrel under understand unduli unequ unfortun uniqu unit univari unknown unlik unrestrict us use ut uxt uzt valid valu var var-model vari variabl varianc variance-covari various varoabl vector versa version via vice violat vk vt wald walk want watson way weak weaker well well-known whether wide without wold word work would write wt x x1t x2t xkt xt xx xx1 xx2 xy xz xz1 xz2 y year yet yoo yt yule z zero zero-mean zt zx zx1 zx2 zz zz1 zz2