why combining works? by spyros makridakis n° 89 / 53...

"WHY COMBINING WORKS?"

by

Spyros MAKRIDAKIS*

N° 89 / 53

Research Professor of Decision Sciences and InformationSystems, INSEAD, Boulevard de Constance, 77305, Fontainebleau,France.

Director of Publication:

Charles WYPLOSZ, Associate Deanfor Research and Development

Printed at INSEAD,Fontainebleau, France.

WEY COMBINING %?ORKS?

Spyros MAKRIDAKIS

Research Professor, INSEAD

FORTHCOMING: INTERNATIONAL JOURNAL OF FORECASTING

Address

July 1989

INSEAD

Bld de Constance

77305 Fontainebleau

France

ktiY COMIUNING WO"r.KS?

Spyros MAKRIDAKIS

Research Professor, INSEAD

Abstract

The purpose of this paper is to explore the reasons why combining

works, discuss the implications involved and propose guidelines for improving

the field of forecasting by exploiting the reasons that contribute to the

success of combining.

Keywords: Time Series Forecasting; Forecasting Accuracy; Combining

There is little doubt that combining improves forecasting accuracy.

This empirical finding holds true in statistical forecasting, judgmental

estimates and when averaging statistical and subjective predictions (Clemen,

1989). In addition, combining reduces the variance of post-sample forecasting

errors considerably (Makridakis and Winkler, 1983). The empirical findings

are at odds with statistical theory and point out the need for major changes

in our basic thinking and approach to statistical modelling and forecasting.

As Clemen (1989) concludes "using a combination of forecasts amounts to an

admission that the forecaster is unable to build a properly specified model.

Trying ever more elaborate combining models seems to add insult to injury as

the more complicated combinations do not generally perform all that well."

FACTORS TLIAT CONTRIBUTE TO MAKING COMBINING WORK

There are several factors that deteriorate the accuracy of

individual forecasting methods and increase the size of errors. Combining

works because it averages such errors. The following factors are a partial

list that contribute to the empirical fact that the accuracy of combining is

higher chan those of the individual methods being combined:

1. Measuring the wrong thing: In forecasting we often need to estimate

damand however damand data is rarely, if ever, available. Thus, instead of

measuring demand we measure such things as orders, production, shipments or

billings. However it is obvious that such proxies of apparent demand

introduce systematic biases in measuring the "real" demand and therefore

decrease accuracy of forecasting.

2. Measurement Errors: No matter what we try to measure there are always

errors of measurement (including clerical and data processing errors) the size

of which can be substantial and systematic. This is particularly true for

disaggregate items but can be also observed on aggregate ones (e.g., GNP - see

Morgenstern, 1963) whose magnitude range from plus of minus 10% to 159.

Measurement errors also include accounting changes, the way the data is kept,

changes in definitions, and what is to be included in the different factors

being used. Even if the size of measurement errors is in the neighborhood of

10%-15% (which is a minimum that applies to highly aggregate macroeconomic

variables) it makes little sense to worry about better methods which are going

to improve forecasting accuracy 5% or 10%.

3. Unstable or changing patterns or relationships: Statistical models assume

that patterns and relationships are constant. However, this is rarely the

case in the real world where special events and actions, fashions, cycles and

so forth bring systematic changes and therefore introduce non-random errors in

forecasting.

-2-

tuai past errors: Availaule forecasting methods select

the best model by a process that depends on how well a model minimizes one-

step-ahead forecasting errors when tested against available data. However,

such models are not necessarily unbiased in predicting future values (in

particular when there are changes in patterns or relationship) and in

forecasting more than one-step-ahead horizons.

CAN COMBINING BE IMPROVED?

Empirical evidence indicates that simple combining schemes (i.e„

using a simple arithmetic average to combine several/many methods) are as

accurate as elaborate ones. The following three factors have been found by

this author to improve the accuracy of combining while maintaining the idea of

using simple combining procedures:

1. Use sensible methods: Various forecasting methods can be checked

empirically concerning their individual ability to accurately forecast.

Alternatively, the findings of major empirical studies can be used to exclude

methods which are consistently worse than others. Once empirical evidence has

indicated a number of models which provide the most accurate results,

combining can subsequently be restricted to these set methods only, thus

excluding some which are clearly inferior (e.g., quadratic exponential

smoothing for longer forecasting horizons).

2. Use complementary methods: Some methods are conservative in forecasting

(for example, single exponential smoothing) while some others are over-

reactive and/or extrapolate past trend in a way that assumes that such trends

will continue uninterrupted during the future. By selecting methods which can

cover a vide range of possibilities the user can combine methods which cover a

wide range of outcomes and which when averaged can also average the

forecasting errors of the methods being combined.

3. Use combining to elicit judgemental inputs: Instead of making judgemental

estimates of future values this author has found it useful to ask decision

makers to indicate the direction of future changes in trends. If the

-3-

subjective judgment of those is that the trend is going to slow down

or become flat, then more weight can Ue given to a method like single

exponential smoothing. Alternatively .f decision makers feel that established

trends will continue, then more weight man be given to linear smoothing. If

the users are not certain the dampen trez.d model can be weighted more heavily.

Thus, by the appropriate selection of forecasting methods to include in the

combining (in particular if they are complementary) . and by deciding on the

appropriate weight of each (or alternatively which methods to combine) a way

can be found to elicit the judgment and knowledge of decision makers while

still harnessing the advantage of using objective and consistent approaches to

forecasting.

COMBINING AND FORECASTING RESEARCH

In addition to more appropriate data geared towards forecasting

applications the methods used to forecast must be also reconsidered. Methods

that fit the past, extrapolate past patterns/relationships and are concerned

with one-step-ahead forecasts are clearly not appropriate. Thus, a serious

effort must develop towards new, creative alternatives that are not based on

the fallacies of constancy of past patterns/relationships which has been the

hidden but prevalent assumption of all statistical forecasting. Some initial

attempts by this author (Makridakis 1990) to go beyond model fitting, and

select methods based on their performance on more than one-step-ahead

forecasts have produced encouraging results. Much more, however, must be done

if forecasting is to become useful and relevant for actual, real-life

applications.

The fact that the accuracy of combining outperforms the individual

methods and/or subjective estimates being combined cannot be ignored and must

be used to guide our search for improving forecasting accuracy. Effort must

be concentrated on gathering the right data and minimizing measurement errors.

Moreover, data must be adjusted to variations that are external to the

generating process (e.g., a strike of some other highly unusual event).

-4-

C()!.;CLUSIONS

Decision makers will benefit by accepting the empirical finding that

combining improves accuracy and reduces the variance of forecasting errors.

Similarly, forecasting researchers ought to test any new methods against a

combination of existing ones. Unless their new method is proven to outperform

the combination it should not be viewed favorably. Finally, forecasting

experts must accept the limitations of available forecasting methods and those

of the data being used and develop alternative approaches to forecasting which

are more realistic and relevant to actual forecasting situations.

-5-

References

Clemen, R.T., 1989, "Combining Forecasts: A Review and Annotated

Bibliography", this issue.

Makridakis, S., 1990, "Sliding Simulation: A New Approach to Time Series

Forecasting", Management Science, Forthcoming.

Makridakis, S and Winkler, R., 1983, "Averages of Forecasts: Some Empirical

Results", Management Science, Vol. 29, No. 9, pp. 987-996.

Morgenstern, 0., 1963, On the Accuracy of Economic Observations, Princeton

University Press, Princeton, N.J.

-6-

INSRAD VORKINC MERS SUIES

*The R L D/Production interface•.

'Subjective estimation in integratingcommunication budget and allocationdectsionss • case study", Jenuary 1986.

*Sponaorshlp and tbe diffusion oforganisetional innovations • preli.inary vite.

'Confidence intervalsr an empiricalInveatigetion for the sertes in the N-Competitlete .

'A nota on the réduction of the vorkveek",July 1985.

'The réal «change rate and the fiscalaspects of • naturel resource discovery•,Revlsed versions February 1986.

*Judgmental blases in sales forecasting',February 1986.

"PorecastIng political rlsks forinternational operationa°, Second Draft:Reich 3, 1986.

•Conceptualising tbe strategic process indiveralfied lira« the rola and nature of thecorporel. influence process*, February 1986.

*Analysing the issues concerningtechnological de -maturite.

' con 'Lydiametry* to 'Pinkhaniration't■ isspecifying advertising dynaasics caretyaffects profitability'.

'The economics of retall firme. RevlsedApril 1986.

' Spatial coepetition à la Cournot•.

'Comparaison intermstional• des marges brute,du commerce*, June 1985.

86/16 8. Espen ECK80 andHervlg M. LANCOBR

86/17 David 8. JEMISON

86/18 James TEBOULand V. MALLERET

86/19 Rob R. VEIT2

86/20 Albert CORNAI,Gabriel HAVAVINIand Pierre A. MICHEL

86/21 Albert CORNAI,Cabriel A. HAVAVINIand Pierre A. MICHEL

86/22 Albert CORthe,Cabriel A. RAVAVINIand Pierre A. MICHEL

86/23 Arnoud DE MEYER

86/24 David CAUTSCBIand VIthala R. RAO

86/25 H. Peter GRAYend Ingo 'MUER

86/26 Barry EICRENCREENand Charles VYPLOSZ

86/27 Karel COOLand Ingemar DIERICKA

86/28 Manfred KETS DEVRIES and Danny MILLER

86/29 Manfred KETS DE VRIES

86/30 Manfred RETS DE VRIES

86/31 Arnoud DE MEIER

86/31 Arnoud DE NETER,Jinichiro NAKANE,Jeffrey C. MILLERand Paire FERDOVS

'Les pria., des offres publiques. la noted'information et le marché des transferts decontrôle des sociétés'.

'Strategic capabllity transfer In acquisitionintegration', May 1986.

' TOWertli an operational définition ofservices', 1986.

' Nostradamus* a knovledge-based forecestingadvisor'.

'The pricing of equity on the London stock«change: seasonslIty and etre pregalum',June 1986.

*Risk-preala ttemsonality In U.S. and Europeanequity markets', February 1986.

"Seasonality in the rlsk - return relationshipssome International evidence, July 1986.

' An exploratory ■tudy on the integration ofinformation systems ln menufecturing'.July 1986.

'A methodology for specificatimm andaggregation in produet concept casting",July 1986.

' Protection', August 1986.

' The economic consequences of the FrancPoincare", Septeaber 1906.

'Megative rlsk-return relationships lnbusiness straterys parados or trulser'.October 1986.

1986

86/01

Arnoud DE SIEUR

86/02 Philippe A. NAERTMarcel VEVERBERGBand Cuido VERSVIJVEL

86/03 Nichael BRIMM

86/04 Spyros NAKRIDAXISand Michèle OISON

86/05 Charles A. VTPLOS2

86/06 Frencesco CIAVAllI,Joit R. SBEEN andCharles A. VTPLOSZ

86/07 Douglas L. KacLACHLANand Spyros MAKRIDAKIS

86/08 José de la TORRE andDavid H. NECKAR

86/09 Philippe C. 11ASPESLACN

86/10 R. NOENART,Arnoud DR MEYER,J. BARBE andD. DESCHOOLMEESTER.

86/11 Philippe A. NAERTand Alain BULTEZ

86/12 Roger BETANCOURTend David CAUTSCBI

86/13 S.P. ANDERSONand Daalen J. NEVE»

86/14 Charles VALDMAN

"Interpreting organizational tests.

' vhy follov the leader?•.

' The succession gamet the rte story.

' Flexibility: the next compétitive battit•,October 1986.

' Flexibility: the nest compétitive battit',kevised Versions Match 1987

86/15 Mlhkel TOMBAK andArnoud DE METER

'Rov the manaterial attitudes of firme withFMS dIffer trou other sAnutacturIng fins,survev results'. June 1986.

86/32 Karel COOLand Dan SM:NUL

Performance dlfferences s'one strategic atour.meabere, October 1986.

1987

87/01 Manfred KETS DE VRIES 'Prisoners of leadership'.

87/02 Claude VIALLET •An empirleal investigetion of international

assit pricing', November 1986.

87/03 David GAUTSCRIand Vithala R.A0

87/04 Sumantra GMOSUAL andChristopher BARTLETT

87/05 Arnoud DE MEYERand Kasra FERDOvS

'A methodology for epecification andaggregation in product concept teatine,Revised Version: January 1987.

•Organiting for innovations: case of theeultinational corporation', February 1987.

"Managerial focal points ln manufacturingstrategy", February 1987.

87/06 Arun K. JAIN, "Customer loyalty as e construct in theChristian PINSON and marketing of banking services'. July 1986.Naresh K. MAL8OTRA

86/33 Ernst BALTENSPERGERand Jean DERMINE

86/34 Philippe RASPESLACHand David JEMISON

86/35 Jean DERMINE

86/36 Albert CORRAY andGabriel BAVAVINI

86/37 David GAUTSCRI andRoger BETANCOURT

86/38 Gabriel BAVAVINI

86/39 Gabriel RAVAVINIPierre MICBELand Albert CORBAT

86/40 Charles VYPLOSZ

86/41 Rasta FERDOVSand Vickhea SKINNER

86/42 Kasra PERDOVSand Per LINDBERG

86/43 Damien NEVEN

86/44 Ingemar DIERICRXCarmen NATUTESand Damien NEVEN

"The role of public policy in Insuringfinancial stability: • cross-country,comparative perspective • , August 1986, RevisedNovember 1986.

"Acquisitions: uyths and raidit'',July 1986.

"Neasuring the market value of • bank, •primer • , November 1986.

"Seasonality in the risk-return relationahiptsome international evidence", July 1986.

•The evolution of ret•iling: • suggested'compatie interpretation'.

"Financial innovation and recent developnentsIn tbe French capital markets". Updated:Septeuber 1986.

"The pricing of comnon stocks on the 8ruaselsstock eltehange: • re-e•anination of theevidenee • , November 1986.

'Capital nove liberalitation and the EMS, •French perspective', December 1986.

•Manufacturing in a nev perspective•,July 1986.

'PMS aa indicator of aanufacturing strategy',Deceaber 1986.

°On the existence of isquilibriun In hotellinesBodel• , November 1986.

•Value added tas and coopetition",December 1986.

87/07 Rolf BANZ andGabriel HAVAVINI


87/09 Lister VICKERT,Mark PILKINCTONand Paul READ

87/10 André LAURENT

87/11 Robert FILDES andSpyrositAKRIDAKIS

87/12 Fernando BAATOLOMEand André LAURENT

87/13 Sumantra GHOSHALand Nitin NOIIRIA

87/14 Landis CABEL

87/15 Spyros HAKRIDAKIS

87/16 Susan SCHNEIDERand Roger DUNBAR

87/17 André LAURENT endFernando BARTOLOME

87/18 Reinh•rd ANCELMAR andChristoph LIEBSCHER

87/19 David BEGG andCharles VYPLOSZ

87/20 Spyros MAKRIDAKIS

87/21 Susan SCHNEIDER


87/23 Roger BETANCOURTDavid GAUTSCHI

'Equity pricing and stock market anomalies',February 1987.

"Leaders vho can't manage', February 1987.

"Entrepreneurial activities of European Klaas',March 1987.

' A cultural vie, of organizational change',March 1987

"Porecasting and loss functions", Match 1987.

"The Janus flead: learning froc• the superlorand subordinete faces of the manager', job',April 1987.

"Multinational corporations as differentiatednetvorks", April 1987.

"Product Standards and Conpetitive Strategy: An

Analysis of the Principles'. May 1987.

"KETAPORECASTING: Vays of itsprovingForecasting. Accuracy and Usefulness",May 1987.

"Takeover atteepts: vhat does the langunge tellUs?, June 1987.

' Managers' cognitive seps for upvard anddovnvard relationshlps', June 1987.

'Patents and the European biotechnology Ing:study of large European pharaaccutical tiras',June 1987.

"Vhy the EMS? Dynamic ga ges and the cquilibriu•policy regine, Nay 1987.

"A nev approach to statistical forecastine,June 1987.

' Strategy formulation: the impact of nationalculture', Revised: July 1987.

"Conflicting ideologies: structural andmot Ivational c.nscquences", August 1987.

"The deaand for retail products and thehousehold production modal: nev vicvs oncomplementarlty and substitutabIllty'.

87/24 C.B. DERR andAndra LAURENT

87/25 A. K. JAIN,

N. K. NALEOTRA andChristian rINS0m

87/26 Roger BETANCOURTand David CAUTSCHI

87/27 Michael BURDA

07/28 Gabriel HAVAVINI

87/29 Susan SCHNEIDER and

Paul SHRIVASTAVA

87/30 Jonathan HAMILTON

V. Bentley MACLEOD

and J. P. TUSSE

87/31 Martine OUINZII andJ. P. TRISSE

87/32 Arnoud DE MEYER

87/33 Yves 002 andAmy SF1UEN

87/34 Kasra FERDOVS andArnoud DE MEYER

87/35 P. J. LEDERER and

J. P. TRISSE


87/37 Landis LABEL



1987

87/40 Carmen MATUIES and

Pierre REGIBEAU

'The internai and esternal careers: atheoretical and cross-culturel perspective'.

SprIng 1987.

'The robustness of NDS configurations in theface of incomplete date, Match 1987, Revlsed:July 1987.

•Desood complememtarities, household productionand ratait assortmente, July 1987.

'Io there a capital shortage in Europe?•,

August 1987.

'Controlling the h:terre-rate risk of bonds:an Introduction to duration analysas andImmunisation strategiee, September 1987.

'Interpreting strategic behavlor: basicassuaptions theaes in organisations', September

1987

"Spatial cospetition and the Core • , August

1987.

"On the optimality of central places',September 1987.

German, French and British aanufacturlogstratégies less different than one thinke,September 1987.

"A process fraaevork for analyzing coopérationbetveen firme, September 1987.

'European manufacturers: the dangers of

cosplacency. Insights froc the 1987 Europeanaanutacturing futures survey, October 1987.

"Coapetitive location on netvorks under

discri■inatory patine. September 1987.

'Prisoners of leadership", Revised version

October 1987.

"Privatiration: its motives and likely

consequences', October 1987.

'Strategy formulation: the impact of nationalculture', October 1987.

'The dark side of CEO succession", November

'Product compatibility and the scope of entre,November 1987

81/41 Cavriel HAVAVINI andClaude VIALLET

87/42 Damien NEVEN and

Jacques-P. THISSE

87/43 Jean GABSZEVICZ andJacques-F. TRISSE

87/44 Jonathan RAHILTON,Jacques-P. THISSEend Anita VESKAMP

87/45 Karel COOL.David JEMISON and

Ingemar DIERICKX

87/46 Ingemar DIERICKXand Karel COOL

1988

88/01 michael LAVRENCE andSpyros MAKRIDAXIS


88/03 James TEBOUL


88/05 Charles VTPLOSZ

80/06 Reinhard ANGELMAR

88/07 Ingemar DIERICKX

and Karel COOL

88/08 Reinhard ANGELMAR

and Susan SCHNEIDER

88/09 Bernard SINCLAIR-

DESGAGNé

88/10 Bernard SINCLAIR.

DESGAGNé

88/11 Bernard SINCLAIR-

DESGAGN6

'Sessonality, sire preatua and the relattenchiebetveen the risk and the return of Prenchcocon stocks', November 1987

'Coebining horizontal and vertical

differentiation: the principic of max-ain

differentiation • . December 1987

'Location", December 1907

'Spatial discrimination: Bertrand vs. Cournot

in • .odel of location choIc • , December 1907

"Business strategy, market structure and risk-return reletionahipss e causal interpretation•.

December 1987.

"Asset stock accumulation and sustalnability

of competttive advantage". December 1987.

"factors affeettng judgemental forecasts andconfidence intercale, January 1908.

'Predicting recessions and octet turning

points", January 1988.

'De-industrialise service for quality', January

1988.

'National vs. corporate culture: implications

for human resource management*. January 1900.

'The svinging dollar: is Europe out of step?'.

January 1988.

'Les conflits dans les canaux de dlatributin•.

January 1988.

"Coupetitive advantage: a resource bal:cd

perspective', January 1988.

'Issues in the study of organizational

cognition", February 1989.

'Price formation and product design through

bidding', February 1988.

"The robustness of son standard auction grume

forms • , February 1988.

'Vhen station:Jr-y strategles are equllibriu■

bidding strategy: The single-crossing

property', February 1988.



08/14 Alain NOEL

88/15 Anil DEOLALIKAR andLars-Hendrik ROLLER

88/16 Gabriel HAVAVINI

88/17 Niehael BURDA

88/18 Michael BURDA

88/19 M.J. LAVRENCE andSpyros MAKRIDAKIS

88/20 Jean DERMINE,Damien NEVEM andJ.F. TRISSE

88/21 James TEBOUL

88/22 Lars-Hendrik ROLLER

88/23 Sjur Melk FLANand Georges ZACCOUR

88/24 8. Espen ECKBO and/kraft( LANGOHR

88/25 Everette S. GARDNERand Spyros MAKRIDAKIS

88/26 Sjur Didrik FLANand Georges ZACCOUR

88/27 Murugappe WUHANLars-Rendrik ROLLER

'Business tires and managers in the 21itcentury', February 1988

•Alexithymia In organisational lite: theorganisation man revisited", February 1988.

•The ioterpretation of strategies: e atudy ofthe impact of ClOs on the corporation•,Match 1988.

•The production of and returns from industrielilSA0V4t1061 an econometrie analysis for adeveloping country. December 1987.

•Market efficlency and equity prieing,International evidence and implications forglobal investine. Match 1988.

•Nonopolistic eorapetitiono costal of adjustmentand the behavior of European employment',September 1987.

*Reflections on 'Vett Unemployment° inEurope*, November 1987, revlsed February 1988.

' Individual bias in judgements of confidence',March 1988.

"Portfolio seleetion by mutual funds, onequilibrium modal", Match 1988.

•De-industrialize service for quality*,Match 1988 (88/03 Revised).

oProper Ouadratic Functions vith an Applicationto AT&T', May 1987 (Revised Match 1988).

' Équilibres de Nash-Cournot dans le marchéeuropéen du gaz: un cas où les solutions enboucle ouverte et en feedback colncident",Mars 1988

•Inforeation diselostiee, means of payment, andtakeover premla. Public and Private tendereffets in France'. July 1985, Shah revision,April 1988.

*The future of forecasting', April 1988.

•Seml-competitive Cournot equilibrium lomultistage oligopolies', Apr11 1988.

' Entry gaie vith resalable capacity',Apr11 1988.

88/29 Nareah K. MALUOTRA.Christian PINSON andArun K. JAIN

88/30 Catherine C. ECKELand Theo VERMAELEN

88/31 Sumantra GHOSHAL andChrlstopher BARTLETT

88/32 Kasra FERDOVS andDavid SACKRIOER

88/33 Mihkel M. TOMBAK



88/36 V1kas TIBREVALA andBruce BUCHANAN

88/37

Murugappa KRISFINANLars-Hendrik ROLLER


88/39 Manfred MS DE VRIES

88/40 Josef LAKONISHOK andTheo VERMAELEN

88/41 Charles VYPLOSZ

88/42 Paul EVANS

88/43 B. SINCLAIR-DESGAGNE

88/44 Essais MAHMOUD andSpyros MAKRIDAKIS

88/45 Robert KORAJCZYKand Claude VIALLET

88/46 Yves DOZ andAmy SHUEN

'Oonaumer cognitive complexity and thediaensionality of aultidi gensional 'ratineconfigurations', May 1988.

' The financial felout from Chernobyl: riskperceptions and regulatory response, May 1988.

*Creation, adoption, and diffusion ofinnovations by subsidiaries of multinationalcorporations • , June 1988.

*International manufacturing: positioningplants for success', June 1988.

' The importance of flexibility Inmanufacturine, /une 1988.

' Flexibility: an important dimension inmanufacturIne, June 1988.

*A strategic snalysis of investeent in flexibleaanufacturing syste■s*, July 1988.

"A Predictive Test of the N110 Nodal thatControls for Mon-stationarity*, June 1988.

"Regulating Price-Liabillty Cogpetition ToImprove Velfare', July 1988.

'The Motivating Role of Envy A ForgottenFactor in Management, April 88-.

'The Leader as Mirror : Clinicol Reflections',July 1988.

*Anomalous price behavior •round repurchasetender effara', August 1988.

*Assynetry in the EMS. intentional orsystealc7*, August 1988.

'Organizational development In thetransnational enterprise'. June 1988.

'Croup decision support systems inplementIlayesian rationalite, September 1988.

'The state of the art and future directionsin combining forecaste, September 1988.

•An eapirical investigation of internationalasset pricing'. November 1986. revlsed August1988.

•Proa intcnt to outcome: • protes. tranevorkfor partnerships', August 1988.

88/28 Sumantra GROSRAL and

'The multinational corporation 63 • netvock:C. A. HARET-En pe-epectives from interorganizatlonal theory'

88/47 Alain BULTEZ,Els GIJSBRECHTS,Philippe NAERT andPiet VANDEN ABEELE

88/48 Michael BURDA

88/49 Nathalie DIERKENS

88/50 Rob VEITZ andArnoud DE NEYER

88/51 Rob VEITZ

88/52 Susan SCHNEIDER andReinhard ANCELMAR


88/54 Lars-Hendrik RÔLLERand Mihkel M. TOMBAI(

88/55 Peter BOSSAERTSand Pierre MILLION

88/56 Pierre MILLION

88/57 Wilfried VAN8ONACKERand Lydie PRICE

88/58 B. SINCLAIR-DESCACNEand Mihkel M. TOMBAI(

88/59 Martin KILDUFF

88/60 Michael BURDA

88/61 Lars-Hendrik OLIER

88/62 Cynthia VAN BULLE,Theo VERMAELEN andPaul DE VOUTERS

"Asymmetric cannibalise betveen substitut.items listed by retallers", September 1988.

"Reflections on 'liait uneeployment' inEurope, II", April 1988 revised September 1988.

"Information asymeetry and equity issues",September 1988.

"Manning expert systems: from inceptionthrough updating", October 1987.

"Technology, vork, and the organisation: theimpact of expert systems", July 1988.

*Cognition and organixational analystes vho's■inding the store?", September 1988.

"Vhatever happened to the philosopher-king: theleader's addiction to pover, September 1988.

"Strategic choice of flexible productiontechnologies and velfare implications",October 1988

"Nethod of moments tests of contingent agameasset pricing models*, October 1988.

"Sire-sorted portfolios and the violation ofthe random valk hypothesis: Additionalempirical evidence and implication for testsof asset pricing eodels", June 1988.

"Data transferability: estimating the responseeffect of future events based on historlcalanalogy", October 1988.

"Assessing economic inequality", November 1988.

"The Interpersonal structure of decisionmaking: a social comparison approach toorganirational choke", November 1988.

"Is mismatch really the problem7 Some estimatesof the Chelvood Gate II Bodel vith US data",September 1988.

"Modelling colt structure: the Bell Systemrevisited", November 1988.

"Regulation, taxes and the market for corporetecontrol in Belgium*, September 1988.

88/63 Fernando NASC/NF.Nr0and Wilfried R.VANHONAGKER

88/64 Kasra PERDOVS

88/65 Arnoud DE NETERand Kasra PERDOVS

88/66 Nathalie DIERKENS

88/67 Paul S. ADLER andKasra FERDOVS

1989

89/01 Joyce K. BYRER andTavfik JELASSI

89/02 Louis A. LE BLANCand Tavfik JELASSI

89/03 Seth H. JONES andTavflk JELASSI

89/04 Rasta FERDOVS andArnoud DE NEYER

89/05 Martin KILDUFP andReinhard ANCELMAR

89/06 Mihkel M. TOMBAI( andB. SINCLAIR-DESGAGNE

89/07 Damien J. NEVEN

89/08 Arnoud DE MEYER andRellmut SCHOTTE

89/09 Damien NEVEN,Carmen MATUTES andMarcel CORSTJENS

89/10 Nathalie DIERKENS,Bruno GERARD andPierre MILLION

"Strategie pricing of differentiated consumerdurables le e dynemic duopoly: e numeriealanalysie, October 1988.

"Charting ■trategic roles for internationalfactories", December 1988.

"Quality up, technology doms.", October 1988.

"A discussion of exact masures of informationassymetry: the exaeple of Niers and Milenodal or the importance of the asset structureof the firm", December 1988.

"The chief technology officer", December 1988.

"The iapact of language theories on DSSdialog*, January 1989.

"MS softvare selectiom: a multiple criteriadecisioa methodologe, January 1989.

"Megotiation supports the effects of computerintervention and confiant level on bargainingouteoee", January 1983:"Lasti ge leprovement in menufacturingperformance: I. seardh of a nev theory",January 1989.

"Shared history or shatved culture? The effectsof tige, culture, nad performance oninstitetionalizatiom te simulatedorganisation'", January 1989.

"Coordinating manufecturing and businessstrategles: I", February 1989.

"Structural adjustment in European retailbanking. Some vire from Industrialorganisation", January 1989.

'Trends in the development of technology andtheir effects on the production structure inthe European Comunity", January 1989.

"Brand proliferation and entry deterrence",February 1989.

"A market based approach to the valuation ofthe assets In place and the grog/thopportunities of the fine, December 1988.

89/11 Manfred RETS DE VRIESand Alain ROLL

89/12 VIlfried VAMIONACKER


89/14 Reinhard ANGES-NAM

89/15 Reinhard ANCELMAR

89/16 Vilfried 9ARHONACKER,Donald LEHNANN and SULTAN

89/17 Cilles AMADO,Claude FAuritEUX andAndré LAURENT

89/18 SrInI BALAK-RISUNAN andMitchell KOZA

89/19 Vilfrled VANYONACKER,Donald LEMANN and►areena SULTAN

•Understanding the leader- ttttt egy interface:application of the s elfe relationshipInterview nethoe, February 1989.

"Ratimatieg dynalet respoase nodale vben thedata are subject te different temporalaigre:ration', January 1989.

•The !aposter syndrome: e disquietingpbenomenem In organisation.' lite", February1989.

'Produc* innovation: • tool for competitiveadvantage• , Match 1989.

•tvaluatleg • fines product Innovationperfornaoce • . Narch 1989.

' Coebining related and 'parse data in linearrelreasloo modela • . February 1989.

' Changement organisationnel et réalitésculturelles, contrastes franco-américains•.Harth 1989.

' Information asyn•etry, market /silure andjoint-ventures: tbeory and evidence•.March 1989

•Cambiales releted and 'perse data in linearregvessioe Bodel'•,Revlsed March 1989

89/20 Vilfrled VANMONACKER "A ratioaal rendes behavior mode' of choice',and Russell RIPER

Revised March 1989

89/21 Arnoud de NETER andKasra FERDOVS

89/22 Manfred RETS DE VRIESand Sydney renov

89/21 Robert KORAJCZYR andClaude VIALLET

89/24 Martin K/LDUFF andMitchel ABOLAFIA

89/25 Roger 88TANCOURT andDavid CAUTSCH/

89/26 Charles BEAN,Edgeond MALINVAUD,rater 8ERNHOLZ,Francesco CIAVAllIand Charles VIPUDS2

•Influence et meavfactoring improvementprogrammes on performance • , April 1989

•vhat is the sole of character InpsychomalysisT April 1989

"Bquity tisk presle and the pricing of fore1gnexchange tisk • April 1989

' The social destruction of reality:Organisation.' con/net as social drameApril 1989

"Tvo esaential charecteristics of retailmarkets and ther etoncalc consequences"March 1989

'Maccoeconoeic policies for 1992: thetransition and atter • , April 1989

89/27 David KRACKRARDT andMartin KILDUFP

89/28 Martin RILDUFF

89/29 Robert COCEL andJean-Claude LARRECRE

89/30 Lars-Bendrik ROLLERand Nikkei M. TOMBAK

89/31 Nichael C. BURDA andStefan GERLACO

89/32 Peter RAM andTawfik JELASSI

89/33 Bernard SINCLAIR-DESCACNE

89/34 Su.antra GHOSBAL andNittin NOIIRIA

89/35 Jean DERNINE andPierre BILLION

89/36 Martin KILDUPF

89/37 Manfred RETS DE VRIES

89/38 Manfrd RETS DE VRIES

89/39 Robert KORAJCZTR andClaude VIALLET

89/40 Halait CBAKRAVARTET

89/41 B. SINCLAIR-DESGACNEand Nathalie DIERRENS

89/42 Robert ANSON andTavfik JELASSI

89/43 Nichael BURDA

89/44 BalajiCRAKRAVARTIffand Peter LORANGE

89/45 Rob VEITZ andArnoud DE METER

"Friendship patterns and cultural attributions:the control of organisational divereity".April 1989

*The interpersonal structure of decisionnaking: • social comparison approach toocganiaational choke", Revised April 1989

•The battlefield for 1992: product strengthand geographic coverage*, Nay 1989

•Competition and Investment in FlexibleTechnologies• , May 1989

•Durables and the US Trade Deficit*, May 1989

•Application and ovalisation of a multi-criteriadecision support system for the dynanicselection of U.S. manufacturiug locations•,May 1989

•Design flexibility in monopsonisticindustries• , Nay 1989

*Requisite variety verses shared values:nanaging corporate-divinion relationahipa inthe M-Form organisatime, May 1989

•Osposit rate caillas* end the market value ofbanks: The case of Femme 1971-1981 • , May 1989

wA dispositiomal appreatà to social netvorks:the case of organixational choire• , May 1989

*lhe organisational foel: balancine . a leader'shubria*, May 1989

"The CR0 blues', June 1989

"An enpirical investigation of internationalasset pricine, (Revised June 1989)

'Management systems for innovation andproductivite, June 1989

'The strategic supply of precisions • , June 1989

"A deve/opment franevork for computer-supportedconflict resolution*, July 1989

"A note on firing costs and severance benefitsin equilibriun unenploynent*, June 1989

"Strategic adaptation in nulti-business firme,June 1989

altanaging expert systems: 4 franevork and casestudy", June 1989

89/46 Marcel CORSTJENS,Carmen MATUTES and

"Entry Encouragement", July 1989

Damien NEVEN

89/47 Manfred KETS DE VRIES "The global dimension in leadership andand Christine MEk0 organization: issues and controversies",

April 1989

89/48 Damien NEVEN andLars-Hendrik ROLLER

"European integration and trade flovs",August 1989

89/49 Jean DERMINE "Some country control and mutuel recognition",July 1989

89/50 Jean DERMINE "The specialization of financial institutions,the BEC model", August 1989

89/51 Spyros MAKRIDAKIS "Sliding simulation: a nev approach to Umeseries forecasting", J uly 1989

89/52 Arnoud DE MEYER "Shortening developmen t cycle times: amanufacturer's perspec tive", August 1989

why combining works? by spyros makridakis n° 89 / 53...

Documents