Top Banner
10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models [email protected] INTERNATIONAL SEMINAR ON EARLY WARNING AND BUSINESS CYCLE INDICATORS 14-16 December 2009, Scheveningen, The Netherlands
34

10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models [email protected] INTERNATIONAL.

Mar 26, 2015

Download

Documents

Paige Dempsey
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points

Jacques AnasDirector, Economic Indicators and Statistical [email protected]

INTERNATIONAL SEMINAR ON EARLY WARNING AND BUSINESS CYCLE INDICATORS14-16 December 2009, Scheveningen, The Netherlands

Page 2: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

IntroductionIntroduction

In 1996, The Chamber of Commerce of Paris decided to investigate the development of a leading indicator for the French economy. This has been the starting point of this detecting system I will present : methodology and real time results.

The concept of turning point must be clearly defined : A hidden event (local extrema, change of regime), quite difficult to predict.

Expectations of users (Government, Central Banks, corporate sector, economists for their prediction) are not identical. If the goal is clear (anticipate an economic upturn or downturn), the communication is an issue (probability, threshold and signal, risk, quantitative implication). There is a need to simplify the messages and to link the signal to an economic analysis.

A tool to be used in complement of other tools (modelisation, short-term analysis by economists). It must be considered as a safety net.

Validation is an issue (ex-post dating to have a reference chronology)

Page 3: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

The concept of detectionThe concept of detection

1. We consider here the follow-up of cyclical movements through cyclical indicators with the purpose to be timely or even leading the movements;

2. It is different than using warning indicators, more structural (imbalances for ex) and potentially leading to crises.

Past TP’s Dating (chronology)

Present TP’s Real time detection (implicitly predicting the future also!)

Future TP’s Predicting turning points (there is an interesting topic: what is a false alarm? It may happen that the signal is invalidated by an external shock or by a quick policy-mix answer.

www.coe.ccip.fr

Page 4: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Turning point detection systemTurning point detection system

A conceptual framework: the ABCD approach

3 indicators:

• IARC: Indicateur avancé de retournement conjoncturel (to predict A and D)

• IESR: Indicateur d’entrée-sortie de récession (to detect B and C)

• IRC: Indicateur de croissance sous-jacenteTo validate the signals of the IARC and IESR indicators

Page 5: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

The framework: the ABCD The framework: the ABCD approachapproach

What kind of a cycle?

• Classical business cycle Level

• Growth cycle Deviation to trend

• Growth rate cycle Variation

Vocabulary issue:

phases of BC : recession and upturnphases of GC: slowdown and rebound phases of AC : deceleration and re-acceleration

www.coe.ccip.fr

Page 6: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Three possible representations

• Classical cycle (in level)• Growth cycle (deviation from trend) • Growth rate cycle

ABCD approach

Page 7: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Page 8: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Three possible sequences of Three possible sequences of downturn movementsdownturn movements

Pure acceleration cycle (« trou d’air »)

• αβ

Growth cycle:

• αA(β)D• αA(βαβ)D with an acceleration cycle during the slowdown

Business cycle: (β is the first optimistic signal)

• αAB(β)CD• αAB(βαβ)CD with an acceleration cycle during the recession

• αAB(βCαBβ)CD case of a double-dip recession

Page 9: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

United States

C ycle d u tauxd e cro issanceo u cycled 'accé lératio n(acce latio ncycle ),rep résenté p arle taux d ecro issanceinstantané d e lap ro d uctio n.

C ycle d esaff aires o u cycleclassiq ue(b usiness cycle ),rep résenté p arle n iveau d e lap ro d uctio n.

C ycle d ecro issance(g ro w th cycleo u d eviatio ncycle ),rep résenté p arl'écart d univeau d e lap ro d uctio n à satend ance .

Les fl uctuat ions de la p roduct ion

Cycle des affaires

.

D..

B.C.

A.

niveautendance

Cycle de croissance

phase de ralentissement

A.

D.

0

phase de récession

écart à tendance

Cycle du taux de croissance.

.B

.C.0

taux de croissance instantané

2

© Coe-Rexecode

Business cycle (billions $ 2000, sa)

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 20109000

10000

11000

12000

13000

14000

AB C

D

A

Growth cycle in %

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010

0

-3

-2

-1

0

1

2

3

Growth rate cycle in %

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010

0

-6

-4

-2

0

2

4

6

Trend growth rateGDP growth (ma3)

B

A

A

D

Page 10: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Euro area

C ycle d u tauxd e cro issanceo u cycled 'accé lé ratio n(acce latio ncycle ),rep résenté p arle taux d ecro issanceinstantané d e lap ro d uctio n.

C ycle d esaff aires o u cycleclassiq ue(b usiness cycle ),rep résenté p arle n iveau d e lap ro d uctio n.

C ycle d ecro issance(g ro w th cycleo u d eviatio ncycle ),rep résenté p arl'écart d univeau d e lap ro d uctio n à satend ance .

Les fl uctuat ions de la p roduct ion

Cycle des affaires

.

D..

B.C.

A.

niveautendance

Cycle de croissance

phase de ralentissement

A.

D.

0

phase de récession

écart à tendance

Cycle du taux de croissance.

.B

.C.0

taux de croissance instantané

4

© Coe-Rexecode

Growth rate cycle in %

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010

0

-6

-4

-2

0

2

4

6

Trend growth rateGDP growth (ma3)

Business cycle billions of euros 2000, sa)

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 20101600

1700

1800

1900

2000

A D

BA

Growth cycle in %

1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010

0

-2

-1

0

1

2

3

4

A

D

A

Page 11: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

A couple of probabilistic A couple of probabilistic indicators applied to France, indicators applied to France, the euro area and United the euro area and United StatesStatesImportance of non linear processes in business cycle analysis

A leading indicator of the growth cycle (IARC)• Based on Neftçi’s a posteriori probability method

applied to leading series (Neftçi, 1982, 1984).

A coincident indicator of the business cycle (IESR)• Based on the univariate Markov switching model

applied to coincident series (Hamilton, 1989, 1990).An important step is the selection of indicators on which

the model is applied. An aggregation method has been developed to combine the probabilities

Page 12: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

1. IARC indicator predicting A and 1. IARC indicator predicting A and DD

)()1)(1()()1(

)()1(1

10

11

011

ttttttt

ttttt xfTPxfTPP

xfTPPP

Recursive bayesian algorythm of Neftçi (1982)

Computed since 1997

Need of a preliminary dating of the growth cycle turning points to select the candidate leading indicators

Multiple criteria (statistical, practical and economic) to select the leading indicators (real, financial and surveys)

Page 13: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Each « k » component allows for the computation of the probability of a coming economic turning point (Rt=1)

)0()01()1()11()1( kt

ktt

kt

kttt

k SPSRPSPSRPRP

)10( ktt

kt SRP

)01( ktt

kt SRP

Prediction of a global turning Prediction of a global turning point based on one component point based on one component

kt

kkkt

k PRP )1()1(

Page 14: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Components of US IARCComponents of US IARC

Consumers anticipations

Manufacturing Inventories (inverse)

New Construction Permits

Stock Market Index (MA3)

Interest Rate Differential (MA3)

Chief Executives Polls

Page 15: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

kt

kkN

k

N

k

ktk P

NRP

N)1(

1)1(

1

1 1

kt

N

k

kk

PN

1

1

Weighted aggregation of the «a Weighted aggregation of the «a posteriori probabilities» (a posteriori probabilities» (a prioripriori weights)weights)

Page 16: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

2. IESR indicator (coincident for B 2. IESR indicator (coincident for B and C)and C)

Modelling coincident variables by Markov Switching models

(St)t K-state first order Markov chain with transition probabilities pij

where p11+ p12+ …+ p1K =1

Parameters estimation: maximum likelihood in conjunction with Expectation-Maximization

Choice of K: comparison of 2 and 3 regimes in terms of cycle replication measured by:

T

ttt PR

TQPS

1

2)(1

1

( ) ( )p

t t j t t j tj

Y S S Y

Page 17: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Decision rules for Decision rules for communicationcommunication

Empirical thresholds for aggregate probabilities

• IARC• 60% and 80% for the aggregate IARC

• SERI• 50% for filtered probabilities and the aggregate probability

www.coe.ccip.fr

Page 18: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

3. IRC indicator3. IRC indicator(temporal disaggregation(temporal disaggregation)

Goal : we need to validate quicly a signalAnswer: by estimating a monthly GDP underlying growth rate ( few revisions, increased timeliness, reduced volatility)

General form of ADL models (Autoregressive Distributive Lag)-

1 0 1 1

2

2,...,

(0, )

t t t t t

t

y y m gt x x

t n

NID

1

tx is the matrix of k endogenous series of size (n x k)

0 1 are vectors of size (n x 1)

and are constantm g

Page 19: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Selection process of the best Selection process of the best modelmodel

• Univariate selection of the best series for estimating the last three years period of definitive GDP (2004-2006)

• Selection of the best three series (in level or in difference)

The choiceThe choice :

- Estimate and extrapolate the model using all past quarterly GDP available at the cost of revising the estimate

or - Estimate and extrapolate using only »final» data at the cost of

missing strong movements which can’t be captured with surveys (present case)

Page 20: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

The selected modelThe selected model for the for the United StatesUnited States

- Housing Index

- manufacturing ISM- Household confidence index (Conference Board)

(1,70) ( 1,22)

1 (67) (2,30) 1 ( 1,60)

0,30) (0,42)

0,98 0,74

0,82 2285 2,12 1,39

0,09 0,13t t t t tY Y X X

1 2 3( , , )t tX V V V

tY : monthly variation of GDP

Page 21: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Performance analysis Performance analysis IARC of France (1997-2006)IARC of France (1997-2006)

Page 22: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

4 recessions in France since 19704 recessions in France since 1970

Milliards d'euros aux prix de l'année précédente chainés (taux annuel)

1970 1975 1980 1985 1990 1995 2000 2005 2010500

700

900

1100

1300

1500

1700

1900

Page 23: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

9 slowdowns (4 are related to a 9 slowdowns (4 are related to a recession)recession)

Ecart à la tendance

1970 1975 1980 1985 1990 1995 2000 2005 2010

0

-3

-2

-1

0

1

2

3

Page 24: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Slowdowns happen when growth is Slowdowns happen when growth is below trend growth ratebelow trend growth rate

Croissance du PIB et de la tendance(variation sur un trimestre en %)

1970 1975 1980 1985 1990 1995 2000 2005 2010

0

-4

-2

0

2

4

6

8

TendancePIB (mm3)

1

2

3

Page 25: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Asian CrisisAsian Crisis

Signal for the related slowdownSignal for the related slowdown At the end of May we could say : “the economic slowdown may have been of short

duration, probably three quarters, and also of low amplitude

100

80

60

40

20

Recherche du prochain pic

0

possibilité deretournement

forte probabilité

de retournement

J FMA MJ J A S ON D J F MA MJ J A SON D

1997 1998

88.2oct.98

Page 26: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Slowdown of 2001Slowdown of 2001

As early as September 2000, the 80 threshold was As early as September 2000, the 80 threshold was reached in the euro areareached in the euro area October 2000 IARC indicator for the euro area published on

November 23, 2000

Page 27: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Signal of slowdown exit in July-August Signal of slowdown exit in July-August 20032003

A signal was given however in February 2002 but in October 2002, we could say that the rebound was aborting

August 2003 IARC indicator for France published on October 3, 2003

Page 28: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Acceleration cycle in 2005Acceleration cycle in 2005

A slowdown was anticpated in June but the signal was A slowdown was anticpated in June but the signal was weak and cacelled out as soon as September 2005”weak and cacelled out as soon as September 2005”

Page 29: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Performance of the indicators Performance of the indicators IARC, IESR and IRC during the IARC, IESR and IRC during the

current cycle current cycle ““How they work together”How they work together”

Page 30: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

EURO areaEURO area

-Signal of slowdown with June 2007 IARC-Signal of recession with August 2008 IESR (published 14th of October)-Signal of exit of slowdown with May 2009 IARC-Signal of exit of recession with September 2009 IESR

Zone euroIndicateur d’entrée et sortie de récession (IESR)

10/12/2009 63

© Coe-Rexecode

2001 2002 2003 2004 2005 2006 2007 2008 200900

0.5

1.0

non récession

récession

Page 31: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

IARC, IRC and GDP for FranceIARC, IRC and GDP for France

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

09-juin-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-06

10-janv-07

21-févr-07

05-mars-07

04-avr-07

04-mai-07

05-juin-07

24-août-07

01-oct-07

09-nov-07

17-déc-07

24-janv-08

25-févr-08

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-09

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-0610-janv-07

21-févr-0705-mars-0704-avr-0704-mai-07

05-juin-0724-août-0701-oct-0709-nov-07

17-déc-0724-janv-0825-févr-0807-mars-08

07-avr-0807-mai-0809-juin-0808-juil-08

03-sept-0825-sept-0829-oct-0825-nov-09

23-déc-08

-3

-2

-1

0

1

2

3

4

5

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d j

2006 2007 2008 2009

27-déc-0610-janv-0721-févr-0705-mars-0704-avr-0704-mai-0705-juin-0724-août-0701-oct-0709-nov-0717-déc-0724-janv-0825-févr-0807-mars-0807-avr-0807-mai-0809-juin-0808-juil-0803-sept-0825-sept-0829-oct-0825-nov-0923-déc-08janv-09

IARC of August 2007 >80 Peak of the growth cycle in the coming 3 months

September 18,2007 signal !

Start of the recession according to IRC!

Page 32: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

IARC, IRC and GDP for FranceIARC, IRC and GDP for France(real time analysis , even for GDP)(real time analysis , even for GDP)

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

25-sept-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

25-sept-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

25-sept-09

25-oct.-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

25-sept-09

25-oct.-09

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

4

j f m a m j j a s o n d j f m a m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

07-mars-08

07-avr-08

07-mai-08

09-juin-08

08-juil-08

03-sept-08

25-sept-08

29-oct-08

25-nov-08

23-déc-08

28-janv-09

25-févr-09

25-mars-09

27-avr-09

27-mai-09

23-juin-09

24-juil.-09

25-sept-09

25-oct.-09

24-nov.-09

IARC of May 2009 <-80 Trough of the growth cycle in the coming 3 months

June 5, 2009 signal !

End of recession according to IRC

Page 33: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

IARC, IRC, IESR and GDP in the United IARC, IRC, IESR and GDP in the United StatesStates (real time analysis , except for GDP)(real time analysis , except for GDP)

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

juil-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

juil-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

juil-09

août-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

juil-09

août-09

sept-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

juil-09

août-09

sept-09

-8

-6

-4

-2

0

2

4

j f m a m j j a s o n d j f ma m j j a s o n d j f m a m j j a s o n d

2008 2009 2010

déc-08

janv-09

févr-09

mars-09

avr-09

mai-09

juin-09

juil-09

août-09

sept-09

nov-09

IARC of May 2009 <-80 Trough of the growth cycle in the coming 3 months

June 3, 2009 signal !

August 28, 2009 statement :

End of recession according to a markovian model based on initial claims for unemployment (date : June)

End of recession according to IRC

IESR = 0.65 in October still no sign of exit of the recession

Page 34: 10 years experience in forecasting turning points Jacques Anas Director, Economic Indicators and Statistical Models janas@coe-rexecode.fr INTERNATIONAL.

10 years experience in forecasting turning points December 14, 2009

Improvements for the futureImprovements for the future

The results of the indicators were quite useful to complement the short-term economic analysis. When the indicator is not going in the same direction of an analysis, it stimulates the discussion and imposes some cautiousness in assertions. At times, it may correct the prediction. But there is a real difficulty to communicate.

The communication with the sequential Netçi’s approach is not easy because it is a recursive process with a discontinuity (semi-parametric approach). A times series approach would be preferable. We may also consider a multivariate approach. Models with more than two regimes may help to consider anticipating A,B, C and D at the same time.

It is rather difficult to make a difference between anticipating a deceleration and anticipating a slowdown. We have not been successful in making this difference but at least we could quickly detect the re-acceleration (which may be an abortion of a rebound for exemple). A particular example is the signal of economic upturn in United States given during the summer 2001 but which was invalidated by September 11.

A route to improve the pertinence of the signal is to increase the threshold from 80 to 90 for example, but we may lose on lead. There is a trade-off between timeliness and minimizing first-type errors.