0 Votos favoráveis0 Votos desfavoráveis

5 visualizações20 páginas.

Dec 02, 2015

© © All Rights Reserved

PDF, TXT ou leia online no Scribd

.

© All Rights Reserved

5 visualizações

.

© All Rights Reserved

- Correlational Research
- Globalization And
- analysis of teeth estimation
- wp0515.pdf
- Commuter Rail and Hybrid Rail Efficiency
- Strategic Planning Practices for Improved Organizational Performance: A Case of MP Shah Hospital, Nairobi
- Ch 3 Forecasting
- Correlation & Regression (Students)
- ICAP-SYLLABUS-2015
- CE122 -14
- 611
- 4
- Chapter 11
- Reverse Code
- w4l1 Causalmodels ANNOTATED FINAL
- pdf (11)
- Math (Regression Theory)
- 10. the Quality of Accrual and Earning - Dechow_Dichev_TAR_2002
- Major Project
- KODE_ICD_10

Você está na página 1de 20

Author(s): R. C. Geary

Source: Revue de l'Institut International de Statistique / Review of the International Statistical

Institute, Vol. 31, No. 2 (1963), pp. 163-181

Published by: International Statistical Institute (ISI)

Stable URL: http://www.jstor.org/stable/1401371

Accessed: 01-06-2015 14:21 UTC

Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at http://www.jstor.org/page/

info/about/policies/terms.jsp

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content

in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship.

For more information about JSTOR, please contact support@jstor.org.

International Statistical Institute (ISI) is collaborating with JSTOR to digitize, preserve and extend access to Revue de

l'Institut International de Statistique / Review of the International Statistical Institute.

http://www.jstor.org

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

STATISTICAL INSTITUTE

Volume31: 2, 1963

SOME

163

A DISCUSSION

VARIABLES:

BETWEEN STOCHASTIC

DOCUMENT*

by

R. C. Geary

The EconomicResearchInstitute,

Dublin

It is thecontentionof thewriterthatthefundamental

problemof themeaningof

in the economiccontextand in general,remainsunsettled.

stochasticrelationship,

It is truethatmuchof theworkin thisfieldis excellent,but real progresshas been

- and theessenceof mathematics

of concluis thecertainty

confinedto mathematics

itis theformulIn theproblemofstochasticrelationship

sionsfromstatedhypotheses.

thatis thetrouble.It is notsurprising

thatauthors- thewriter

ationofthehypotheses

is one - tendto returnto the topic at intervalsof yearsto shake its uneasybones.

but there

We may,or maynot,politelymentionone anotherin ourlistsof references

is littleevidencein our individualwritingsthatwe have deeplystudiedthe others'

thinking;and the presentpaper is no exceptionto thissorryrule. More like poets

thanscientists,

each of us seemsto wantto workthisone out forhimself;thestruggle

is in one's own soul.

the

in whatfollowsare verysimple,deliberately

The mathematics

so, to highlight

the

of

to

characteristics

in

as

the

stochastic

particular,assumptions

hypotheses

the writer'sexpressionof viewswill be forthright,

residualerror.Also deliberately,

to inspireor to provokedebate.It was an Irishstatesmanof otherdayswho said that

in speechto attainmoderationin ends.Perhapsit is hightimeworkers

he exaggerated

in thisfieldgettogether.

I.

WHAT IS REGRESSION?

relationship,

dependentvariablesbeing the causes and the dependentvariablethe effect.With

Y=-o

+

X

+ u

a givenvalue forX, calculatingY a + 3X and addinga randomvariableu. Simple

regressiontheoryis concernedwiththeestimationof a and p froma seriesof pairs

limitsof theseestimates,as well

of observations(X, Y) and discussingtheconfidence

the varianceof the randomelementu - the latterbeingof major imas estimating

theconfidencelimitsof theestimateof the averagevalue of

portanceforestimating

it becomesclearwhythereare in generaltwo reas

X.

Viewed

cause-effect,

Y, given

thecause of Y,

forone lineX is, byhypothesis,

case:

lines

in

two-variable

the

gression

forthe otherY is the cause of X and thereis no reasonwhytheseshouldcoincide,

evenwhenthenumberof pairs of observations(the data) is infinite.

the

oneselfto thetwo-variablecase, thebasic problemconfronting

Stillconfining

the

statistician

is, givena scatterdiagramin (X, Y), to findthelaw, ifany,governing

havingregardto probability,or stochastic,theory.We have already

relationships,

* Paperpresented

of

of theEconometric

at theJointEuropeanConference

Society,theInstitute

Dublin 3-7 September1962.

of Mathematical

Sciencesand theInstitute

Statistics,

Management

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

164

mentionedtwo such relationships,

the two regressionstraightlines: therecould of

to which

in character

coursebe curvilinear

relationships,

regressional

(i.e. cause-effect)

whether

randomsamplingtheorycan be made apply.We have testsfordetermining

of whatkindcan it plausibly

thereis any relationshipand, ifthereis a relationship,

be regarded.Attentionwillbe confinedto thelinearcase.

have recognisedthatthere

Fromtheearlieststatistical

times,however,statisticians

betweenrandomvariables.

otherthan regressional,

were conceivablyrelationships,

Theysaid (moreor less) letus abandonthenotionofanyspecialrole(e.g. a particular

foreach variable:be quiteneutralas to the

variableregardedas a cause or an effect)

role of thevariable,treatthemall as equals,and see whathappens.Call theresulting

"associative","neutral",or whatyou will.I shall,in what

relationship"functional",

What is thelaw governingthejoint movementof

use

the

term

associative.

follows,

The

of

observations?

pairs

questionposed in thisway indicatesthattheassociative

in

sciencewhereso oftenwe can

viewpointpredominates the fieldof experimental

believein theexistenceofa law,ifonlywe couldfindit,our difficulty

beingdue solely

to errorsof theordinarykindin our observations.

An earlyfavouriteas an associativelaw was the line (or plane) of closestfit,i.e.

the straightlinewhichminimisesthesumsquaresof distancesfromthepointobserstochastvations.The troublehereis that,in general,theprocedurecannotbe justified

sensibleon practicalgrounds.A stochastic

theoryhas been

ically,thoughitis perfectly

developedon the followinglines([1], [2]). In the simplestcase of two variableslet

themodel be

Yt =

(1.1)

xt

Xt = xt + u,

Yt = Yt + vt

t= 1, 2, . . . , T,

(ut,v,) about

whichnothingelse is assumedexceptthattheyare independent

of one anotherand

of (xt, yt) the "true"measuresand thatall theirmomentsexist.The problemis to

estimatethe coefficient

p fromT sets of observations.All variablesare assumed

cannotbe solvedusingthe

measuredfromtheirmeans.The problemas formulated

variancesof Xt and Yt and/orthe covariance(Xt, Y,) since(whenT is indefinitely

large)theuse ofthesemomentssupplyonlythreeequationsto obtainfourunknowns

Eu2, Ev2. Instead,recoursemustbe had to highermoments,

(,Ex? (E = expectation),

or the mathematically

cumulants(L for (X, Y), X for

equivalenttwo-dimensional

defined

in

the

(x, y))

by

identity (s, t):

E exp (sX + tY) - exp {I

L(i,j) s' t1/i!j! }.

1, J

.E

But,fromtheindependence

assumptionsabout theerrorvariablesu, vand using(1.1)

(1.2)

(1.3)

E exp (sX + t Y)

whencethefundamental

relation

(1.4)

L(i,j) = (i,j)

whenbothi andj are non-zeropositiveintegers.But,from(1.1),

Eexp(sx

= exp Z X(i,j)xiyJ/i!j!

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

165

whereXkis thek thcumulantof x. Equatingcoefficients

of s ti ,

kP5j

= X(i,j)

Hence

X(i,j + 1)

Xk+1 ~j+1=

+

kk 1,U).

It followsthat

(1.5)

L (i,j + 1)(1.6)

1,j) = 0

L(i + 1,j) = 0 .

k

(1.7)

: PkXk= 0

=1

i=

Xk= Xk+ Uk

coefficients,iare then

(1.8)

1,2,...,k

f PiL (c

, c2 ...,

Ci +

Ci+ 1, ...

Ck)

= 0

of relations(1.8) which

T

is

constitute

the

and

sufficient

conditionsforthe

(when

indefinitely

large)

necessary

of themodel(1.7). It can easilybe shownthat,whennumberof setsT

acceptability

of observationsis finite,consistentestimatesof the L functionscan be foundfrom

theoperation

(1.2) (and analogouslyin thegeneralcase ofk variables)bysubstituting

1T

T t=1

for E. There is an asymptoticrandom samplingtheoryavailable for the theory

outlinedabove [2]. It suffers

fromthedisadvantagethatit is computationally

difficult

usinga deskmachineexceptwhenthenumberofvariablesis twoor three,or perhaps

in the"Reiersolcase" ofinstrumental

variables- see (vii) below.Also, sincewiththis

theorywe musthave (in general)recourseto cumulantsof powergreaterthantwo,

the errorvariancestendto becomelarge. That is whyone musthave morethan a

sneakingregardforempiricaldeviceslike the straightline (or plane) of closestfit,

whichinvolvesonlythevariancesand covariances.

Followingare some remarkson associativerelationship:(i) The theoryis not applicablewhentheobservations(X1, X2,... Xk) arejointly

forthenall thecumulantsof morethanone discussionand of

normallydistributed,

2

than

are

zero so thattheequationsystem(1.8) reducesto thetrivial

powergreater

0 - 0.

involvedin the IrishmanBoyle's (17th Century)Law using

formallythe coefficient

theLaw is

Boyle's original25 pairsof observations.For constanttemperature

Log P +

P log V = Constant

The estimatep of is

P = L(3,1) / (2,2)=

1.00404

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

166

whichscarcelyrequiresa significance

testto establishinsignificant

difference

from

In

a

in

lecture

the

writer

remarked:

Paris,

unity.

"Remarquonsincidemment,

que la loi de Boyles'appelleloi de Mariotteen France,

avec la memelogique qui faitque la loi normale,decouvertedans des conditions

diff6rentes

par de Moivre et Laplace, s'appelle quelquefoisloi de Gauss. Sans

tous

les pays regoivent

6ventuellement

doute,

justiceen moyenne".

(iii) Thereis a non-lineartwo-variable

theoryalso availablethoughherenuisance

which

under

certain

additionalhypothesescan be estimated

parametersintervene,

fromthedata.

(iv) Linear associativetheorycan be regardedas a generalizationof regression

theorythrowingsome lighton the latter.In theusual notationthemodelis

k

Pi + u,

Y= i=1

YE

all variablesmeasuredfrommeans.The standardequationsforestimating

thePi by

bi are

1

bk

bi

bi

=

=

X2 + ...

k.

X, Xi + ...0 ++ T SYXi

TT'

T XkXi, i 1,2,..,

ofearliertheory,

therearek + 1variablesandthecovariances

Now, fromtheviewpoint

involvedare equal to thecorresponding

cumulantsso that,forassociativetheorythe

covariancecoefficients

are estimablesince

E YXi = Eyxi

But

E Xi X = Exixj,

i 6 j.

EX2= Ex + Eu

in whichthereintervene

thenuisanceparameters

Eu?. The regression

equationsthereforebecomeassociativeonlywhenEu2 = 0, i.e. ui = 0, i = 1, 2, . , k. Hence by a

..

circuitousroutewe come to the basic assumptionof regression

theory,namelythat

it yieldsassociativevaluesofthecoefficients

variablesare

onlywhentheindependent

observedwithouterror,the singleerrorvariable in the model pertainingto the

dependentvariableY.

data as a sample,

(v) The R. A. Fisherstochasticmodel envisagesthe regression

or realisation,froma universein whichthe independent

variablesare the same for

all samples.J. Berkson[3] has, however,isolateda lineartwo-variable

case in which

regressiontheoryyieldsthe correctassociativeestimatethoughboth variablesare

subjectto error.In theBerksoncase whenwe thinkour measureof theindependent

variableis X it is reallyx where

x= X

u,

u beingtherandomerrorassumeduncorrelated

withX. The contrastwithassociative

theorywillbe noted: heretheobservation

X=x+u

comparedwithca in the Fishercase. In the Berksoncase the regressionof Y on X

The Fishersignificance

yieldsa consistentestimateof thecoefficient.

theoryapplies,

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

167

oftheindependent

in measurement

variable

thoughthepricepaid fortheimprecision

is thattheerrorvarianceV is now

V=o2

+p2G2

for

case is available [4] but therethenuisance

a2v

the

Berkson

linearsignificance

theory

which

intervenes

can, however,be estimatedfromthe observations.

parameterca

of

of

is indefinitely

number

sets

observations

the

When

largein thelinearasso(vi)

ciativecase oftwovariablesitis easyto showthattheassociativelinemustlie between

the two regressionlines.This need not necessarilybe the case whenthe numberof

pairs of observationsis limited.In factin the generalassociativecase, as remarked

earlier,therandomsamplingerrorvarianceof P tendsto be so largeas to givevery

aberrantresults.

and when

(vii) Whenone has availablemanyeconomictimeseriesall inter-related

one's model of severalbehaviouristic

equationsonlya fewof thesevariablesappear

one can use the

in each equation,forthe consistentestimationof the coefficients

to 0. Reiersol([5], [6]), theinstruments,

variablemethod,due essentially

instrumental

in regardto any equation,beingthevariableswhichdo not appear in the equation.

a particularcase of(1.8) above,theequationsystemfortheestimation

This constitutes

oftheterms

of thecoefficients

onlycovariancessincethecoefficients

pinowcontaining

to be zero.

are

assumed

error

thebiassing

in E Xi2,throughwhichintervene

variances,

from

their

Y

X

and

two

contains

variables

(measured

only

Suppose the equation

model

is

the

and

means)

X=x+u

Y= y +Uv

v

Y=y+

y= px,

u and v beinguncorrelated

withu and v. Then

withX and Y but uncorrelated

correlated

additionalvariableZ,

so that

of which

EXZ = ExZ

E YZ = Eyz = P ExZ

P=EYX/EXZ

measuredfromtheirmeans)is a consistent

(wherethethreevariatesarenotnecessarily

a certain

estimate.Thereis a theoremthatwhen(X, Y, Z) are normallydistributed

as theStudent- Fishert [7]. The writerwouldwishfora

functionof b is distributed

simplerproofof thistheoremthanthatwhichhe found,forsucha proofmightlead

i.e. forany numberof variables.

to a generalisation,

variableshould

i.e. if u is zero, theinstrumental

Of course,if X is non-stochastic,

be Z = X itselfwhen the solutionis the regressionone, forthe reason (Markov)

variablesZ = X yieldsminimumvarianceof the

that,of all possibleinstrumental

theoremis thatthematrixX

case thecorresponding

estimateof 3.In themultivariate

The instrumental

of

the

coefficients.

estimates

of

the

variance

thegeneralised

minimizes

consistency

of

statistical

the

merit

has

estimation

coefficient

for

variableprocedure

As we knowfromsampling

inefficiency.

but at the cost of a measureof asymptotic

forgreaterefficiency

practice,sometimesit maybe expedientto sacrificeconsistency

in calculation.

in estimationand simplicity

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

168

II.

A PROPERTY

OF REGRESSION

COEFFICIENTS

ratherfundamental

is notto be foundin any

It is curiousthatthefollowing

property

of thetext-bookswhichthewriterhas consulted,thoughhe is aware thatothercolleaguesknowit,and indeedit mightbe suspectedby anyonefamiliarwithregression

theory.Let theoriginalmodel,in matrixform,be

y= =pX+u

(2.1)

variablesinto any two groupsof kl and k2 variablesso thatk = k, + k2. Model

(2.1) can thenbe writtenin theidenticalform

y = P1X + P2X2+ u,

forthe secondtermon the

wherenow i, is (1 x kj), Xi is (k, x T) and similarly

is

matrix

the

of

be

the

residual

of

Let

regression X1 on X2. The property

right.

V,

coefficient

vector

thattheestimateb, of is identicalwiththeregression

transposed

p the generalisationof a propositiondue to R. Frisch and

cl of y on V,*. This is

F. V. Waugh [8], provedforthecase of k2 = 1. The maininterestof thisproperty

variablesincreases

in itsgeneralformis computational;as thenumberofindependent

is an increasingly

efficient

method(usinga deskmachine)

(beyond4 or 5) partitioning

in termsofnumberof computationaloperaof computingtheregression

coefficients

thenumberskl and k2,givenk, which

tionsinvolved.It is evenpossibleto determine

affordsthemostefficient

partition.

Anotherformof the propertyis thatif z is the residualmatrixof the regression

matrixbl.

y on X2 the regressionof z on V1 also yieldsidenticallythe coefficient

a Cobbfor

in

found

coefficients

This is why thepost-warperiodV. Cao-Pinna [9]

for

of

function

the

form

Douglas

Italy

(2.2)

q = constx H KY e t,

(2.3)

and K = capitalstockat constantpriceshad (as Cao-Pinnafound)coefficients

P and

almost

K

In

H

were

from

fact

and

different

zero.

linearly

increasing

q,

y insignificantly

as theregression

witht = timeso thatwhentheestimatesof p and y are interpreted

of the (small) and probablyrandomresidualswhenthe effectof t is excludedfrom

The writeris scepticalabout

is understandable.

log q, log H and log K, thenul-result

resultsfor many countriesfor the inter-war

period,where 3 was so oftenfound

both,on thegroundsthat(i) with

equal to about 2/3and y to 1/3,highlysignificant

K as capitalstock(and notcapitalin use or capitalactuallyconsumedin theproductionprocess)formula(2.3) could notpossiblybe a good theoryforexplaining

year-toyearvariationin q and (ii) thatthe"good fits"foundweredue to spuriouscorrelation

helpedby thepronounceddip of all variables(including,exceptionally,

K) in thedetake suffinot

1929-35

of

could

which

the

term

at

pressionperiod

exp obviously

cientaccount.

III. HAVE INDIVIDUAL

REGRESSION

COEFFICIENTS

OBJECTIVE SIGNIFICANCE?

Since regression

is essentially

a cause-effect

theonlyvalidobjectofthe

relationship

exerciseis to be able to estimateon averagethe value of y corresponding

to given

valuesoftheindependent,

orcausal variables.The coefficients

aretherefore

collectively

* The

proofis a prettyexercisein matrixmanipulationat studentlevel. G. Tintner[12] has a theorem

verylike thisthoughhe does not use a matrixmethodto proveit.

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

169

useful.In mostcases,especiallywheneconomictimeseriesare involved,theindividual

are devoid of interestor significance.

coefficients

variablecase, one has determined

the coeffiSuppose that,in a threeindependent

cientsbl, b2and b3by least squareprocedureand writes

(3.1)

Y = bl xl + b2X2 + b3 x3

say b2 as "a riseofonein x2entailsa riseofb2in y whenx, and x3 remainconstant".

The troubleis thattheceterisparibuspartdoes not obtainexceptin theveryspecial

and rarecase ofxl, x2 and x3 beingmutually

a case whichneverarises

uncorrelated,

when one is dealingwithmacro-economic

timeserieswhenone can findveryhigh

correlationsindeed; in factin a paper [10] of manyyearsago the writerfounda

correlationof .97 betweenemployees'compensationand consumers'perishable

goods for U.S.A., 1921-38(usingH. Barger'sdata) and, even afterthe removalof

termsto degree7 in timethecorrelation(of residuals)remainedas highas .93.

It mayevenbe of some littleinterestto considerthevalue ofy, in the threeindeto a value x2 of x2 whenaccountis takenof

pendentvariablescase, corresponding

concomitantvariationsin x, and x3, withinthe logic of regressiontheory.Let x1

and x3 be the average or expectedvalues to be assignedto x, and x3 respectively

consequentto thevalue x2 beingassignedto x2. From simpleregression

(3.2)

x -

SX2X1

X2;

X3

X2 3

X2

to thesevalues of xl, x2, x3. Then from(3.1),

= bl x + b2x2+ b3x3

Yl

(3.3)

= x2 (bl Z2 X1+ b2Z x2 + b3Z x2X3)

the

the coefficients,

But, fromthe second of the standardequationsfordetermining

expressionin bracketsequals Z x2y. So finallywe have

(3.4)

Z x2y X2

thesimpleregression

ofy on x2. The rightanswerto thequestionoftheaverageeffect

on y of a rise of unityon x2 (any independentvariable)is furnished

by the simple

regressionofy on x2, no matterhow manyothervariablesor equationsthereare in

the system.

A rationalmeaningcan therefore

in manycases be attributed

to thesinglecoefficient

in simpleregression,

and perhapsonlyin sucha case. At theotherextremeone must

be extremely

scepticalon statisticalgroundsalone about themeaningor usefulness

of individualcoefficients

in the many-variable

case when one so well knows that

small changesin the basic data (sometimeswell withintherangeof accuracyof the

data) can resultin substantialchangesin theestimatesof thecoefficients.

The writeris aware thatthe statementthatvalues foundforindividualmultiple

coefficients

is meaningless

has ratherdevastating

formarginal

regression

implications

deanalysisin practice.One of the best-known

applicationsis thatof price-income

mand analysisbased on timeseriesin theform(withtheusual notation)

(3.5)

log q = c+ P log

+ y log

t + u,

All use subject to JSTOR Terms and Conditions

170

The specialProvidence

as priceand incomeelasticity.

wherep and y are interpreted

that

ordain

which watchesover virtuousanalystsmay

log p/P and log YIP are

seemsinvalid.If we

if

are

usual

but

not

the

uncorrelated

elasticity

they

interpretation

a

to

which

a rationalmeaning

on

and

t

we

obtain

coefficient

log p/P

P'

regresslog q

contextcan be attached:no matterhow manyothercausal variables

in theelasticity

or not,

shouldbe in thetrueformulaforlog q and whethertheseare inter-correlated

whenall theothervariathevalue ofthecoefficient

estimaterepresents

theregression

bles assumetheiraveragevalue consequenton log p/P havinga givenvalue. But in

for all

equal to P' and yetP seemsto be thepriceelasticity

(3.5) P is not necessarily

values of log YIP whenthe effectof timet is eliminated.Of course,(3.5) in its revalid answerto

gressionformand undertheusual conditionswillafforda perfectly

theproblemofexpectedq consequenton givenvaluesofp, P, Y and t. Rathersimilarly

any theoryof marginalratesof returnto labour and capitalbased on partialdifferentialsof a productionfunctione.g.

q =f (H, K)

(3.6)

thatH - hoursworked

are dubiousunlessone caresto sponsorthecurioushypothesis

toolsand machines

without

ofK- capitalstock.Can hoursbe worked

are independent

or vice versa?

The foregoingconsiderationsalso lead one to the conclusionthat much of the

and comparais irrelevant

preoccupationwiththeerrorvariancesof thecoefficients

tivelyunimportant.

coefficients

have

theindividualregression

In one specialcase ofmultipleregression

But in thiscase,

variablesare uncorrelated.

a meaning,namelywhentheindependent

the

are exactlythosewhichwould be foundon regressing

of course,the coefficients

i.e.

of

variables

on

each

the

variable

by

simple

separately,

independent

dependent

theoriginal

to theproblemoforthogonalizing

Thisfacttendssomeinterest

regression.

in which

of lineartransformations

independentvariablesystem.Thereis an infinity

in matrixformas follows

thismaybe affected,

Z

B X,

(3.7)

matricesand B is (k x k).

whereX and Z (k x T) are the originaland transformed

in theoriginalindependents,

has themeritthatit is symmetrical

One transformation

orthovariablesare theprincipalcomponents,

namelythatin whichthetransformed

has no stochasticimgonal, of course,to one another[11]. This transformation

identicalwiththe originalin X

plicationswhatever:analysisin Z is mathematically

will

withthevalue of y givenZ

of

X

be

identical

since the estimatedvalue y given

into Z by (3.7). In the contextof economictimeseriesthe

when X is transformed

principalcomponentmaytakeup thegreaterpartof thevarianceofy and so impart

an objectivevalidity

tothesimpleregression

coefficient

ofyonthisprincipalcomponent.

In forecasting

whatusuallymattersis thevarianceoftheforecastwhich,unfortunately for forecasters,

depends absolutelyon the unit residualvariance 02 of the

seriesused to determinethe regression,

even if thisseriesis verylong and even if

and all

one makes the most favourableassumptionsabout stabilityof coefficients

therest.In fact,ifin simpleregression

Y=a + b X,

(3.8)

whereX is givenand Y is theestimateof Y, then,as is well-known,

(3.9)

VarY =

02

-+T

(X -X)2/

)2

(X-

= 0 (T-1) .

All use subject to JSTOR Terms and Conditions

171

However,thistakes care onlyof the expectedor averagevalue of Y. For actual Y

forecastedthevarianceis

VarY = a2 + Var Y,

(3.10)

whenthe numberof observationsT

is large.If a is of the orderof theyearto yearchangein Y no valid forecastcan be

made in the shortterm.In the longertermwe may be in bettercase, sincewe can

reasonablyassumethatwe are concernedwiththe"average"or normalsituationand

changesfrombase to reference

yearmaybe substantial.

IV.

REMARKS

ON SYSTEMS OF EQUATIONS

Whenthewriterwas activelyresearching

on relationsbetweeneconomicvariables

about fifteen

or twentyyearsago, it was in the highestdegreehereticalto take the

attitudeoflettingthefiguresspeakforthemselves.

No, one musthave regardto what

was called, and perhapsis stillcalled, "economictheory".Actuallythe formulaof

thepriestcraft

is enshrined

in thesubtitleoftheEconometricSociety"An International

for

the

Advancement

of EconomicTheoryin its Relationto Statisticsand

Society

Statistics

and Mathematicswelland trulyin theirsubordinate

Mathematics",putting

A

view

was

taken

of the notionthatthe problemof establishing

place. verypoor

between

economic

time

seriesshouldbe approachedin a neutralway,

relationships

without,however,any abdicationof good sense,withthe object of findinga set of

complete(in thesenseof thewriterin [7]) linearrelationsin whichtheerrorvariance

ofthesystemas a whole- perhapsthegeneralised

variance- was as smallas possible.

He well recallsthe shock of disagreement

at a sessionof InternationalStatistical

Institute

manyyearsago whenO. Morgenstern

(withno doubtdeliberateexaggeration)

remarked"let's throwall thefiguresintoa computerand see whatcomes out at the

otherend". He was possiblythe onlypersonpresentwho had any sympathy

with

The writerdoes not assertthatthelack of successwhichhas attended

Morgenstern.

efforts

to setup economicequationsystemswas necessarily

due to theshacklesofthe

he does knowthatshacklesofanykindareinimicalto scientific

priestcraft:

objectivity

and development.Whilepayinga warmtributeto the so veryfewdevotedworkers

who dared to applytheirtheoryto actual data, the totalvolumeof appliedworkin

to deriveworkingmacro-economic

modelshas beenpunyin theextreme.That

trying

theseefforts

were not on a largerscale was due in a degreeto the scepticism,the

As Larochefoucauldalmostremarked,

inspissatedgloom,ofthepriestcraft.

theywere

not too unhappyin theireconometricfriends'misfortunes.

Those who genuinely

want to know in measuredtermshow the economicsystemworksmustsevertheir

connectionwitheveryprejudiceofso-calledeconomictheoryand setup computational

on a vastlylargerscale in thefuturethanin thepast.

experiments

Of coursein practicethefewdevotedmodel-workers

to be

did notallowthemselves

spancelledby economic theory.Having made obeisance,theyset down perfectly

sensibleputativerelationships

identities)

(apartfromtheaccountingand definitional

such as currentconsumptionbeingrelatedto current(and possibly)laggedincome,

thatoutputwas relatedto manpowerand capital,thatgovernment

was

expenditure

relatedto taxesand all therest.One does notneedto be an economistto surmisesuch

formsof relationship.Thosewho triedto verifyanythingwhichmightproperlybe

called"economics"havenothadhappyexperiences:

is a caseinpoint.

theroleofinterest

As alreadyremarked,

few

of

the

in

of

coefficients

very

systems equationshave any

in themselves;thosewhichhave are those occurringin equationswith

significance

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

172

is forecasting

is implied

onlytwo variables.That the main objectof model-makers

in thearrangedequalityofthenumberofcurrent

variables

to

the

number

endogenous

of equations. Such equalitypermitsthe derivationof the reducedform(afterthe

ofthecoefficients),

i.e. ofexpressions

foreachofthecurrent

determination

endogenous

variables.It is high time that model-makers

variablesin termsof predetermined

and assertthatpredominantly

should shed theirpreoccupationwiththe coefficients

is forecasting.

the objectof model-making

relationAnymodelswithwhichthewriteris familiarare redolentof cause-effect

endogenousvariable

ships.Usuallyone findsthateachequationconsistsofonecurrent

on the leftand one or more currentendogenousvariablesand predetermined

(includinglaggedendogenous)variableson theright;itis evidentthatthelattervariables,

in thethoughtofthemodel-maker,

are regardedas causesand thevariableon theleft

as theeffect.Sincenumberof equationsequals numberof currentendogenous,each

of thelatterhas a solo partin a particularequation.Now thisis surelya verycurious

a cause

way to imaginehow thesystemworks.How can a variablebe simultaneously

and an effect?

Is one to imaginethatthecausativevariableis to be lagged"a little"

in time as comparedwithostensiblythe same variableas an effect?

But, if so, in

to rejointhat

is

not

are

two

variables

not

one.

It

there

and

quitesatisfactory

principle

one doesn'tknow.One wayofdealingwiththis

thevalueswillbe onlya littledifferent:

is, ofcourse,to inserton therightwitheach current

endogenousvariablethe

difficulty

same variablelaggedone timeunit,withtheidea thatthetwovaluesweightedby the

coefficients

are equal to one laggedvalue,i.e.

x, + P x,_= X,_,Oc+ p= 1.

This devicewould have someplausibility

ifthevariablewas moreor less continuous

in time,whichit rarelyis. Considerablymoreattentionmustbe givenin thefuture

is a useful

thanin thepast to thetimeintervalwhetherone believesthatcause-effect

when

results

To

to

or

not.

the

of

economic

expectgood

approach

relationships

study

one has imposed(usually)the year as the timeunit,givingone the choice only of

which

or effect

aftera wholeyearis to expecttoo much.Relationships,

simultaneity

are obviouslysignificant,

aftera timelag of a week or a month(whenone has the

statistics!)oftenvanishwhenthe figuresare totalledfora year.Of course,modelmakerscannotbe faultedfornot workingwithshorttimeunitswhenthe required

statisticsare not available.

From theforecasting

pointof viewwhatwe reallywantto knoware thevalues of

some k variablesin yearT + 7 whenwe knowthedata foryearst = 1, 2, ..., T.

We have no directinterest

in whatcaused what;wejust wantto know.The equation

all economicmodel-makers

systemis a meansto thisend,but,as alreadyremarked,

have followedthecause-effect

route.The writersuspectsthatthisapproachhas sometimesinvolvedthemin logicalcontradiction

at thestagewhentheoriginalequation

is

coefficients

system(with

purestimated) expressedin reducedformforforecasting

As

statistical

poses.

every

neophyteknows,havingwrittenthe simpleregressionof

Y on X in theform

Y= a + bX,

one cannotstatethat

X= (Y-a)/b,

in any verymeaningful,

as distinctfromformal,way. Yet thisseemsto be thekind

of thingone does withtransformation

to reducedform.It is the writer'sgrowing

convictionthatwhenseveralvariablesappearin an equationtherelationbetweenthem

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

173

at anyratewhentherelationship

is associative

shouldbe associative,notregressional;

substitution

of variablesof the typeindicatedis always permissible.Such sanctity

attachesto the fullmaximumlikelihoodmethodof coefficient

estimation,thatit is

commonlyoverlookedthatML does not produceassociativeresults.

In somemodelsitis customary

to introducevariablestermed"policyinstruments",

level of

usuallythose variableswhichare underthe directcontrolof government,

taxationand the like, the problembeing to determinethe effecton othermacroOne mustbe verycarefulhere.

economicvariablesof changesin the instruments.

Suppose themodelconsistsof a singleequation

(4.1)

Yt =

PXt-1

Ut, t = 1, 2, ... , T,

coefficient

3 (presumablynegativein sign) is estimatedby regressionand T is insincext_

-, at a timeunitback,

large.Theremightappearto be no difficulty

definitely

can be conceivedas the cause ofyt,but in the ordinary

meaningof words,xt,_cannot be regardedas the "cause" of y,. Yet on occasiony is a targetwithvalue r and

the problemarises of findingthe value of x, say ?, the "instrument",

whichcorresponds to thistarget.

From (4.1),

= (r - u) /p,

whereu is a nuisanceerrorterm.To obtaintherightaveragevalue of the?, theinstrument

variablecorresponding

to givenr, we mustassignto u its averagevalue u

to r. This value is foundas

corresponding

(4.2)

u=

(4.3)

in (4.2),

Then,on substitution

-=

(4.4)

Eyu

/Ey2.

E

r (Ey2-

Eyu) /Ey2

Exy /Ey2 ,

wants to know the lagged tax level correspondingto targetincome and should

and not the

regresslagged tax on currentincometo findthe regressioncoefficient

otherway about), yet one wondersif this is always recognisedwhen the issue is

complicatedby manyvariablesand manyequations.

The writerwould verymuch like to provokea discussionon thispoint at this

Conference.He wouldlikehis colleaguesto addressthemselves

to thislittleproblem

in particular.Let themodel of a consumptionfunctionbe

(4.5)

C= pY+ u

0 thenC - 0. Can I estimatep by

thatwhen Y

(4.6)

=c

Y,

of C on Y? Beforeyou answertoo hastilylet me warnyou that,despitethe initial

hypothesesof zero associationof Y and C, the regressionwill containa positive

constantterm,contraryto hypothesis.In fact,in the associativecase, the model is

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

174

C=c+u

Y= y + v

(4.7)

c= py

whereu and v are errortermswithmeanszerouncorrelated

butunknownvariablesc and y. Whenthenumberofsetsofobservations

theinherent

is indefinitely

large

Ec /Ey = EC/EY

(4.8)

of C on Y theabsoluteterma' is givenby

But fromregression

a' = EC- P' EY,

(4.9)

where

(4.10)

From (4.7), (4.9) and (4.10) and usingthe assumedpropertiesof u and v, we find

C' =

(4.11)

P a2

EY/E(Y-EY)2

(as it willalwaysbe) and a -= 0.

The writer'squestion"Are therelationswe wantto be causativeor associative?"

is not a rhetoricalone; he reallywantsto know. There are conceptualdifficulties

in regardingtherelationship

as associative,in particularin anyeconomicvariableX

are supposed

partx, to whichtherelationships

beingdecomposableintoan inherent

to pertainand a purelyrandompartu, so thattheobservation

X

x + u,

betweentime

timeseries.From the writer'sown work [10], associativerelationship

betweenseculartrendswhereastheresultspreviously

seriestendsto be relationship

mentioned

tendtoshowstrongrelationships

betweenresidualsaftertrendsareremoved.

but not suitablefor

suitableforlongertermforecasting

Are associativerelationships

short-term?

associativerelations(and thiswill be by no means

If one succeedsin establishing

or paradoxes

there

in

is

easy practice,though

plentyof theory)no contradictions

of thekindsindicatedabove can arise.

of substitution

V.

SYSTEMS

conceivedas an errorof measurement,

of

due to humanfallibility

or thelimitations

the measuringinstruments.

It was easy to attribute

ranthe

of

conceptually quality

domnessto errorsofthiskind.Now in thosedaystheastronomical

and otherphysical

laws whichhad emergedor were emergingwere simplein character:oftenindeed

theirformcould be inferred

theactualobservations

theoretically,

beingrequiredonly

- a simplesituationindeed.In thesocial sciences,on theotherhand,

forverification

thelaws,ifanyobtain,are immensely

morecomplicatedthanin thephysicalsciences.

Theoreticaland qualitativeeconomicsgiveus butlittleguidancein themathematical

formof theselaws. Geometricaland mathematical

economicsuse onlythe simplest

functionalformsand these,one suspects,are selectedmorefortheirsimplicity

and

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

175

for classroompurposesthanforany convictionon the part of theirinventorsthat

reality.You willhavenoticed,forexample,thatintimeseriestheyalmost

theyrepresent

the solutiony = Cext, whichno economictimeserieshas obeyed

have

invariably

He showedlittledisbetween

consecutive

years.Came the econometrician.

except

to

in

than

in

the

work

functional

firstdegreethough

higher

relationships

position

theremaybe thisto be said forhim,injustification,

thatin introducing

laggedterms

intohis equations,he was implicitly

usingthecalculusof finitedifferences,

just one

fromlineardifferential

removetherefore

equations,which,as you are aware, can

involve solutionsof highfunctionalcomplexity.One qualitysharedby economists

alike is a distinctpreference

for the dialecticand for matheand econometricians

matical abstractionsas againstthe brutalisingdisciplineof numericalcalculation.

Inevitablythereappeared discrepanciesbetweentheoryand practice.The "expected"valueswerefoundto deviatein greateror lesserdegreefromthetruevalues,

To makeup forthediscrepancy

an errorterm

ifone can so politelytermthestatistics.

and

was introduced.Stochastictheorywas thenavailable forcoefficient-estimation

withR. A. Fisher'stestsof consistency,

and thewelltestsof significance,

efficiency

knownpropertiesof maximumlikelihoodestimation.By far the greatervolumeof

data weretimeseriesforwhichit was foundnecessaryto make a considerableextento thefactofserialcorrelation

in the

sion ofexistingstatistical

theory,due principally

statisticaltimeseries.

The errortermin anyequationis themeasureofwhatwe don'tknow.In thesocial

is farlessthaninthecase ofexperimental

sciencesknowledgeoflaw ofcause and effect

we have to make thebestuse of whatwe can get

science.In economicinvestigation

and the statisticsavailable tend to be of unsuitabledefinition,

inaccurateand informof thelaw

complete.In addition,we don't knowin advancethemathematical

It is reallyonlyin thefieldof samplingsocial surveysthatthe

or laws of relationship.

is in anything

like thesituationof theexperimental

economicstatistician

statistician

in havinghis measurements

and thewholeplan of his inquiryundercontrol.

of therandom

It is not as clearlyrecognisedas it shouldbe thattheintroduction

variablecompletely

economicsin thebroader

changedthecharacterof mathematical

sense.Any reasonablesystemof behaviouristic

equationsin timeserieswill contain

lagged as well as currentendogenousvariablesand it is customaryto arrangethat

the numberof endogenousvariablesequals the numberof equations.The formal

whichare

solutioncontainsa termlinearin the randomvariableswithcoefficients

moreor less estimablebut thiserrortermis of the same orderof magnitudeas the

As remarkedearlier,in mathematical

economicswithout

variableto be determined.

the errorsthe solutionis usuallyin exponentialor Fourierform:in any realistic

solutionthesetermswilllong sincehave vanishedwhenaccountis takenof theerror

alteredby the

terms.The pointis thatthecharacterof thesolutionis fundamentally

introduction

of errorterms:the formalsolutionfor each endogenousvariablefor

currenttimeis an expressionlinearin theerrortermsand in theexogenousvariables,

back in timeto thestartof theseries.

stretching

The specialproblemsof economictimeseriesposed theoretical

problemsof special

solved.These

to themathematician

and manyof thesehave beeningeniously

interest

branchofmathematical

problemsand theirsolutionhavejustlyendowedthisparticular

statisticswitha highprestige,certainlya muchhigherprestigethan it deservesfor

its practicalusefulness.

we are askingthaterror

In economicequations,singleor in sets,beguiledbytheory,

termto do too much.Surely,in reason,we cannotexpectmuchofa stochastictheory

whenwemaketheerrortermstandforall thevariableswhichshouldbe in theequations

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

176

in thevariableswe

if onlywe knewwhattheywere,forthe errorsof measurement

of thelaw of relationship.

have includedand fortheinevitablesimplification

Since all the seriesexhibitedthephenomenonof serialcorrelationusuallyin emtheimmensely

phaticdegreeand sincethesimplemodelscould notpossiblyrepresent

it

was

inevitable

of

the

economic

thatthephesystemcorrectly,

complicatedworking

ofresidualsshouldappearin theresults.It was surelynot

nomenonofautocorrelation

themodel

thatif thisphenomenonis admittedas part of thehypothesis,

surprising

resultsin practice.The postulatethattheresidualsare (i)

could notyieldsatisfactory

variablesand at thesame timeinclude,as it must,

of thepredetermined

independent

of variables(necessarilyseriallycorrelated)not explicitin the

(ii) the contributions

in terms,forthereason

equationsbecausetheyare notknown,seemsa contradiction

the residualswhichencompassthemcannot be

that the unknownsand therefore

of theknownpredetermined

variables.

postulatedas independent

of residualsin

It is the writer'sconvictionthatthe hypothesisof auto-regression

is

equation systemsbased on timeseries(howeverattractiveit is mathematically)

ofthecoefficients

in

inadmissablefromthepracticalpointofview.If,afterestimation

any particularhypotheticalequation, the residuesexhibitthis phenomenonthe

equation shouldbe rejectedor, by trialand error(addingfreshvariablesor taking

othersout), the originalequation should be amendeduntilone attainsnon-autothisis a highlyempiricist

correlatedresidualerrors.Admittedly

pointof view.The

writerbelievesthat,whenall theoriginaltimeseriesare so highlyautocorrelated,

the

of adequacyof relationship

bestcriterion

is, thattheresidualsshouldbe foundto be

completelyrandomby thevon Neumannor othertests.

thehypothesis

If thisviewpointbe acceptedthenmodelsincorporating

of residual

are erroneous.Considerthemodel

auto-regression

Yt =

---

(5.1)

t-1 + Vt,

wherethe vtare autocorrelated.

vt= vt,_+ ut,

and non-correlated

withvt-_,vtbeinguncorrelated

whereutare non-autocorrelated

withyt-i. The problemis to estimateP froma seriesof Ty' s. In myopinionthis,the

simplestpossiblecase ofthekindofthingwhichis notuncommonin morecomplicated

More correctly,

from(5.1) in (5.2),

form,is a wrongformulation.

by substitution

(5.2)

Yt -

Yt-1

(Yt-1 Yt-2) + Ut

or

Yt= (c +3- ) Yt-1- PYt-2+ Ut.

(5.3)

The lattersurelyis the law we are seeking.We are interested

in estimating

(oc+ P)

and ac3 forthepurposeof forecasting

The

in

and

the

formulation

are

oc

original

P

Yt.

of no interestin themselves.*

And hereis an exampleof rathera different

characterdiscussedby manyauthors,

thoughthepresentglossis thewriter'sown. The modelis

(5.4)

Ct = P Yt -+ u,

Yt = Ct +- It

t = 1, 2, ..., T

* I am indebted

to M. H. Quenouille

fortheinteresting

thatif,as appearsto be theonly

observation

a and 3,givenby (5.1) and (5.2) froma set of

method,thesolutionof theproblemof estimating

is via(5.3),then,sinceac P and ap are symmetrical,

observations

theestimates

ofa and 3 are infromone another.

distinguishable

All use subject to JSTOR Terms and Conditions

177

ut random,Ct and Yt endogenousand It exogenous.The object is to estimate 3,

to consume,thoughwe shall see thatit isn't.

presumablydesignedas thepropensity

First(and thereis a hinthere)tryto setup thissystemin thisformgiventhecolumns

of utand It as wellas thecoefficient

p. You willfindyou cannot.You can onlydo so

by reducingtheformto either

1

ut

(5.5)

Yr= t + ut, P'

ut - 1=-3'

of

"I +

(5.6)

u,

Actuallywhensolved by least squares the last two equationsare foundto be consistentin that

as shouldbe thecase since

S=

1.

withtheestimatesP' and 3". The point

directlyfromthe firstof (5.4) is inconsistent

is that(5.4) is a falseformulation

thatat givenlevel

whichstates,ifit statesanything,

of Y, we expect(subjectto a randomerror)that Ctwill have a givenvalue, i.e. a

consumptionfunction.What we are reallysayingis that Y, and It or Ct and It are

economictheory,a capital/outputtheory,or, equivalently,

related,a quite different

a capital/consumption

theory.This maybe a trivialexamplebut it raisesthewhole

ofbehaviouristic

questionofthevalidityofthesolutionofa mixture

equationsand the

identities

and

of action

as

freedom

accounting

allowingoneself, is common,complete

as regardseliminationof variablesbeforeproceedingto solutionby maximumlikelihood or othermethods.

When we statethatan equationin our economicmodelis

o I+

Yt= tx

i=1

whatis our pictureof thereality?Of course,we have no illusionsabout thelinearity

of the equation: we usuallycrossthathurdle(whichwill troubleus no morein this

section)by assuming,sometimesagainstall theevidence,thatwe are concernedonly

withthe estimationof "small" deviationsfromsome norms,whenwe have Taylor's

Theoremto sustainus. If (5.7) is a classical regressionequation the assumptionof

linearityaffectsonlythe dependentvariable Y since the X's, beingpre-determined,

can have anyfunctional

formwhatever,

e.g. X2 can be X12,or whatwe wish.But can

be

about

the

classical

modelin economicapplications,that

anyone happy

regression

Y on the one hand and theX's on the otherhand have so verydifferent

stochastic

properties;forwhatwe are sayingis that Y is envisagedas exactlyequal to a linear

with

witha randomscattering

of valuesu uncorrelated

expressionin theX's together

thelinearterm?Whateverviewbe takenof theassociativeconcept,surelyone must

be unhappyabout thisas an imageof economicrealityor anything

approachingit?

Or do we say that Y is exactlyrepresentable

by a linearexpressionof whichwe

know onlyk + 1 terms?That,in fact,u has thefollowingform:(5.7)

(5.8)

ut =

* Pk+j Xk+j.

j=1

t,

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

178

to use a

or the Xk+j. (Of course it would be moresensiblein thesecircumstances

singlesymbolforeach term;the expressionis writtenin the way it is to pointthe

thatvar (u) is an ordinarymagnitude:

analogywith(5.7)). We assumethroughout

if it were "small" therewould be no problem.If we knewthe values of the Xk

+j

thenanyk + k' + 1 setsof ( Y; Xi, Xk+j) wouldserveto obtainthe exact values of

the (c; i, k+j), consistentwiththewhole T > k + k' + 1 setsof values.If the

correlationof each of theX1witheach of theXk+j were exactlyzero the values of

the pi foundwould be exactlyequal to thosefoundby regressionfrom(5.7). What

regressionhas done is to givethefirstk + 1 termsof a linearexpressioncontaining

k + k' + 1 terms.If thecorrelations

betweentheX's in thetwosets,insteadofbeing

fromzerointherandomsample

different

all exactlyzero,weresimplynotsignificantly

wouldbe unbiasedestimates

ofT setsofoperationsthentheji calculatedbyregression

of thetruevaluesPi.

variableswould

to believethattheknownand unknownindependent

It is difficult

was

dividethemselves

up intotwogroupslikethis,unless,of course,therelationship

the

associativeand completein whichcase the errortermwould merelysynthesize

thenumbersare all mutually

randomerrorsin the( Y; Xi). In theknownset,typically,

withthe

in timeas well; sincenon-correlation

correlatedand each is auto-correlated

of

the

latter

that

members

it

is

knownset is postulatedin theunknownset,

unlikely

seemsto disqualifythemas timeseries.

are auto-correlated

and lack of thisproperty

betweentheresidualu and the

The processof regressionimposesnon-correlation

variablesXi in (5.7). If in truthu has the form(5.8) wherethe X variablesexist

(thoughwe do not knowthem)and if,infact,some of thesevariablesare correlated

intheestimates

causesa distortion

withsomeoftheX's intheknownsetthenregression

of Piwhichare notconsistent

withtheirtruevalues.If thesetruevaluesare supposed

to have somekindofeconomicvalidity,

so muchtheworsefortheregression

process.

on subone

finds

in

If, afterestimationof the coefficients

regression,

(5.7)

by

Pi

in time,this

stitution

thattheestimatesoftheindividualresidualsare auto-correlated

resultseemsto establisha primafacie case forthe factthatu has in factthe form

variable

(5.8) withat least one of thecoefficients

Pk+j non-zero,the corresponding

values Xk+j having ordinarymagnitudesand the variable having the expected

In a wordthevariableexistsand theobviouscourseis

propertyof auto-correlation.

in theresiduals,

to go look foritinsteadofpostulating

ofauto-correlation

theproperty

of whichno practicalgood can come.

VI.

INTEGRAL

SOLUTION

OR

INDIVIDUAL

LEAST

SQUARES?

if he

As he attacheslittleimportanceto individualcoefficient-estimation,

neutrality.

had to choose he would inclinetowardsthesolutionof each equationin the system

ifone is unableto use

theplane ofclosestfitto regression,

byleastsquares,preferring

the full associative solution. The writerfranklyconfesseshimselfto be a rank

As we don't know the laws of economicsand probablywill neverknow

empiricist.

them,let'sgo findwhathas workedbestovera seriesof yearsby all kindsof experithemost

ments,by trialand error.WhileML appliedintegrally

yieldsasymptotically

efficient

estimatesof the coefficients,

it by no meansfollowsthatthisis necessarily

thecase whenthetimeseriesis short.A good deal of imprecision

is likelyto remain

in thebestmodelsand in thesecircumstances

simplestmethodsofsolutionseembest.

If one attachesno specialimportance

but

to theestimation

ofindividualcoefficients

- and if,of course,one believesin the

wishesto use the systemonlyforforecasting

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

179

leastsquaresor ML methodsof solution- thereseemsto be no good reasonwhyone

shouldretainoriginalform,withall itsdifficulties

ofcalculation,in solvingthesystem.

Instead,proceedat onceto reducedform,and solvethat.The originalform,ifsoundly

variableswhichshouldappear

based,will,ofcourse,serveto definethepredetermined

in each reducedformequation,i.e. thevariableswithpresumednon-zerocoefficients.

There are no identification

problemswithreducedformand each equation can be

solved separatelyby least squares.

VII.

CONCLUSION

probablyagree thatthe sciencehas somethingto do witheconomicmeasurement,

i.e. economicstatistics.

Yet in a recentverylargeissueofEconometrica

onlyone-third

of the pages in the contribution

sectionweredevotedto articleswhichcould be regarded as "econometric"by this definition.The writeris aware of the Society's

Policy Statementof 1954 but perhapssince then mattershave got a littleout of

control.No one can objectto mathematics

as thenoblestexerciseofthehumanspirit

but the disproportionbetweenmathematicsand applicationin statisticalscience

is to be regretted.

All articlesacceptedforEconometrica

shouldat leasthave applicationin mind,eveniftheythemselves

do not containapplications.Theyshouldtherefore be couched in termscomprehensible

who are not

by potentialpractitioners

in the offensivesense of the term.The Annals of Mathematical

mathematicians

Statisticsand Biometrikapresumablyexist to accommodatepapers of adequate

qualitywhichare not applied papersin the senseindicated.The writerspeaks with

some feelingon thismattersincein theissue of Econometrica

referred

to therewas a

shortarticleon an important

the

moment

which

interests

him

at

yethe

topic

greatly

was stoppedin histracksat an earlystagebythestatement

"letN (X) = {j : xi = C}",

knows

X beinga transposedvector.It maywell be thateveryyoungmathematician

whatthis means; the presentwriter,in the language of his grandchildren,

"hasn't

a clue"; an additionalsentenceor twomighthave made all clear.Existencetheorems,

are all verywell in theirproperplace but

strongertheoremsand epsilon-mongering

thatplace shouldnot be a journaldevotedto an appliedscience.

Surelythevastpotentialofthemodemdigitalcomputer,

possiblea thourendering

sand computationalcombinationswhereone could not have been envisagedbefore,

should be harnessedto econometricends. Let us not favoura prioriany particular

modelbuttrythemall. The needis urgentforthewholeworldhas turnedto planning

and forecasting

and we econometricians

are in the sorrypositionthat,withall our

on theonlygroundsthat

recommend

theory,we have so littlethatwe can confidently

matter,namelythatour theoryhas been triedout and foundsuccessfulin practice.

statistical

Certainit is thatthe greatmajorityof plannersuse the most elementary

and

devicesin makingtheirforecasts.Econometricresearchschools in universities

institutes

shouldturntheirresourcesoverwhelmingly

towardsapplication,relegating

in thelightofcomputational

results.

theoryto theroleofgeneralguide,to be modified

At the same timewe should exerciseall the pressurewe can on officialstatistical

organisationsto give us the statistics,particularlyat the macro-economiclevel,

moreadvanced

whichwe require.National accountstatisticsin eventhe statistically

in scope and come out too late. Yet with

countriesare ofpoor quality,are insufficient

the advent of planningthese statisticshave assumed essentialimportance.As a

are

I knowhow anxiousmycolleagueseverywhere

one-timegovernment

statistician

to improvethese statisticsand my strictures

are not addressedto them: for good

This content downloaded from 147.188.128.74 on Mon, 01 Jun 2015 14:21:48 UTC

All use subject to JSTOR Terms and Conditions

180

whichencompassall economicstatistics,

thecooperation

nationalaccountstatistics,

of all sectorsof theeconomyis necessary.The elementmostinimicalto thedevelopon the past of industrialists

mentof these statisticsis apathyand disinterest

and

businessmengenerally.

To end, may I summarizethe principaldiscussionpointsin the paper proper:ofeconomicequationstheindividualcoefficients

havelittlesignificance;

(i) In systems

all thatreallymattersis theestimationformulae.

equations should we seek associativeor

(ii) In establishingsets of behaviouristic

cause-effect

relationships?

of auto-regression

of residualsin timeseriesis unusefuland mis(iii) The hypothesis

in

the

economic

we

withactual data

context; mustgo on experimenting

leading

in whichresidualsare trulyrandomin timeand in

untilwe findrelationships

else.

everything

(iv) Is reducedformtheonlyvalid form?

REFERENCES

relationsbetweenrandomvariables.Proceedings

of theRoyalIrish

[1] Geary,R. C. Inherent

Academy(A), 47 : 6. 1942.

thegeneraland thesamplingproblemwhenthe

[2] Geary,R. C. Relationsbetweenstatistics:

oftheRoyalIrishAcademy(A), 49 : 10. 1943.

samplesare large.Proceedings

Journal

Statistical

45. 1950.

[3] Berkson,J.Aretheretworegressions?

oftheAmerican

Association,

functional

betweentwovariableswhenone variableis

[4] Geary,R. C. Non-linear

relationship

Journal

controlled.

Statistical

48. 1953.

oftheAmerican

Association,

and othermethods

of confluence

analysisbymeansof lag moments

[5] Reiersol,O. Confluence

9. 1941.

analysis.Econometrica,

setsofvariables.Uppsala. 1945.

analysisby meansof instrumental

[6] Reiersal,O. Confluence

oflinearrelations

between

witherrors

systematic

partsofvariables

[7] Geary,R. C. Determination

of observation

thevariancesofwhichareunknown.

17 : 1. 1949.

Econometrica,

as comparedwithindividualtrends.Econo[8] Frisch,R., Waugh,F. V. Partialtimeregression

1. 1933.

metrica,

etempirique

de l'6cod'uneprevision

[9] Cao-Pinna,V. Validit6theorique

globalede la croissance

nomieitaliennede 1958a 1970.Dans: Europe'sFuturein Figures.NorthHollandPublishing

1962.Chapter4.

Company,Amsterdam,

between

economictimeseries.Journal

[10] Geary,R. C. Studiesin relations

oftheRoyalStatistical

Society(B), 10 : 1. 1948.

5 : 3.

ratioand statistical

Statistician.

[11l Geary,R. C. The contiguity

mapping.TheIncorporated

1954.

G. Econometrics.

[12] Tintner,

Wiley,New York,1952.Chapter11.

RESUME

Dans cettecommunication

I'auteurexaminequelquesproblemes

fondamentaux

dans la theorie

des relationsentredes variablesstochastiques.

La regression

une relation

impliqueessentiellement

caracterecause-effet,

les variablesind6pendantes

l'effet.

6tantles causeset la variabled6pendante

On ne doitpas confondre

la regression

avecunerelationdu typeassociatif,

dontla theorie

lin6aire

estesquissredansle texte.Dans la theorie

associative

il n'estpas besoinde faireappelg l'hypothese

cause-effet.

Dans la regression

de plusieursvariablesles coefficients

individuels

ou

sontsans signification

saufseulement

dansle cas specialde variablesindrpendantes

Le seulbut

importance

non-correlees.

Aplusieurs

de la regression

variablesestd'estimer

de la

(pourla pr6vision

etc.)la valeurmoyenne

variabled6pendante

En 6conom6trie,

c'est

pourdes valeursdonn6esdes variablesindependantes.

All use subject to JSTOR Terms and Conditions

181

dansle cas de la regression

a unsens.A titred'exemple,

seulement

on montre

simplequele coefficient

des prixet des salairesApartirde seriestemporelles,

il fautcalculer

les 61asticit6s

que, pourestimer

chacunede ces variabless6par6ment

la tendance.

par une regression

simpleapresavoir61imin6

L'auteurse demandesi la notionde systeme

estutileen 6conom6trie.

d'6quationsde structure

dans le cas de la former6duite,

une seulevariable

C'est seulement

ofichaqueequationrenferme

endogeneque la theoriea unevaleurpratique,pourla prevision.

L'auteurpose la questionde l'utilit6pratiquede I'hypothese

des erreursdans

d'auto-r6gression

la theseque leserreurs

8tresuppos6es

doivent

lesseriestemporelles.

absolument

II soutient

al6atoires.

Apartird'exemples

bien-connus

entraine

Il montre,

6conomiques

que l'hypothese

d'auto-r6gression

les relations.

des 6nonc6sincorrects

concernant

"Afinde

sous formede questionsa la finde la communication,

Tous les 6nonc6ssontr6sum6s

servirde base Aunediscussion.

All use subject to JSTOR Terms and Conditions

- Correlational ResearchEnviado porSari Kusumaningrum
- Globalization AndEnviado porOmar Hasan
- analysis of teeth estimationEnviado porAisyah Rieskiu
- wp0515.pdfEnviado porIrene Ragona
- Commuter Rail and Hybrid Rail EfficiencyEnviado porspj2106
- Strategic Planning Practices for Improved Organizational Performance: A Case of MP Shah Hospital, NairobiEnviado porJASH MATHEW
- Ch 3 ForecastingEnviado porAnonymous iEtUTYPOh3
- Correlation & Regression (Students)Enviado porvksingh_188005
- ICAP-SYLLABUS-2015Enviado porSania Ali
- CE122 -14Enviado porAce Bihis
- 611Enviado porVictor Chen
- 4Enviado porMAYUGAM
- Chapter 11Enviado porsolomon_vicencio
- Reverse CodeEnviado porMiana Yana
- w4l1 Causalmodels ANNOTATED FINALEnviado porGlennizze Galvez
- pdf (11)Enviado porclaudia_claudia1111
- Math (Regression Theory)Enviado porAlina Borisenko
- 10. the Quality of Accrual and Earning - Dechow_Dichev_TAR_2002Enviado porTasiman
- Major ProjectEnviado porSubrata Mahapatra
- KODE_ICD_10Enviado porNahdiah Dhea O
- Previous year paperEnviado porManishaParmar
- Correlation and How It is Useful for GovermentEnviado porDarshil Vaghani
- Output BaruEnviado pornoviakus
- ergEnviado porumbu
- Bcg Comp Chapter4Enviado porgaurav1249
- Roman AssignmentEnviado porolgapp
- QTEnviado pornirali
- MB0024 SET 2Enviado pormuravbook
- CorrelationEnviado poranand
- SenSemRegress4s14Enviado porRahulsinghoooo

- Robert CastelEnviado porCarlos Mejía Reyes
- Strangleman-2015-The British Journal of SociologyEnviado porCarlos Mejía Reyes
- Kanungo R 1992 Alienation and Empowerment Some Ethical Imperatives in BusinessEnviado porCarlos Mejía Reyes
- Kanung R 1990 Culture and Work Alienation Western Models and Eastern RealitiesEnviado porCarlos Mejía Reyes
- Alfred Kinsey. Sexual Behavior in the human male.Enviado porCarlos Mejía Reyes
- Schwartz 1994 - Are There Universal Aspects in the Content of Human ValuesEnviado porCarlos Mejía Reyes
- Www.jstor.org Stable Pdfplus 10.2307 189663Enviado porCarlos Mejía Reyes
- Jowell Roger Comparative ResearchEnviado porCarlos Mejía Reyes
- Work and Occupations-2012-Fernández-Macías-157-82Enviado porCarlos Mejía Reyes
- work_europe_96_va (1)Enviado porCarlos Mejía Reyes
- White Collar Ameri 00 MillEnviado porJoli Anjela
- Work Employment Society 2011 Bergman 561 8Enviado porCarlos Mejía Reyes

- Term Paper & MLA CitationEnviado porMunu Sagolsem
- 02 Panini and PingalaEnviado porShyam Mishra
- Sample IB Prescribed Title EssaysEnviado porJoel Caffey
- Kazar in OffEnviado porNames Orwell
- The Seven Liberal Arts and SciencesEnviado porplastico1617
- 20140413icm Proceedings ZieglerEnviado porRhizhail
- PrologEnviado porcars7
- Modulated Logics and Flexible ReasoningEnviado porWalter Carnielli
- Mfcs Hand BookEnviado porAnonymous vopE9EmDF
- Venn Diagram Technique for testing syllogisms.pptEnviado porUrvashi Sikka
- Chapter 15Enviado poreuhsaha
- Ware2017, Kant's Deductions.pdfEnviado porOwenWare81
- automatatextbook2.pdfEnviado porUmesh Gowda
- 1. SET THEORY.pdfEnviado porArlyn Calderon
- MGT303 Assignment 4 v.1(1)Enviado porGareth Thomas
- 02-CombEnviado porJamal
- Toc Qn Model 2017Enviado porAnonymous LfIbKZ6
- Digital Electronics Tutorial.docEnviado porfirmanrusydi
- week 2 (types of meaning).pptxEnviado porNoureldin Mohamed Abdelal
- Logic.pdfEnviado porcorazonpuro
- Moore. Arguing With DerridaEnviado porjuanevaristo
- Logical FallaciesEnviado porhnugroho_4
- Kant Prolegomena - vs. Hume HandoutEnviado porEmoEvo
- Bauder Rachel 201606 PhD ThesisEnviado porMark Francis
- Morley's TheoremEnviado porpeter
- Lubb Al-Lubab (the Kernels of Kernels) - A Short Treatise on WayfaringEnviado porDunja دنيا Rašić
- Deleuze_Speculative_and_Practical_Philos.pdfEnviado porClaudia Mongini
- SAT Essay RubricEnviado porMamaher
- Advanced Mathematical Structures for ComputingEnviado porugwak
- Cone Cct NesEnviado porFernandoFierroGonzalez

## Muito mais do que documentos

Descubra tudo o que o Scribd tem a oferecer, incluindo livros e audiolivros de grandes editoras.

Cancele quando quiser.