nowcasting real economic activity in the euro area · 2016-11-18 · nbp warsaw workshop on...

NBP Workshop on Forecasting Warsaw, 21 November 2016

Nowcasting real economic activity in the

euro area Assessing the impact of qualitative surveys

Authors: Raïsa Basselier ([email protected]) David de Antonio Liedo ([email protected]) Geert Langenus ([email protected])

2

Outline of the presentation

1. Introduction

2. The analysis of news

• Mapping of news into forecasting updates for euro area growth

• Empirical results of the benchmark case

3. How does the impact change when…

• we ignore the release schedule?

• we ignore the presence of data revisions?

4. Variable selection

5. Forecasting accuracy

6. Concluding remarks

4

Goal of the paper

► Quantify the real-time impact of survey data on forecasts for GDP growth

Retail Sales

(DE)

Industrial

Production

(DE)

Industrial

Production

(EA)

Sentix GDP (BE)GDP (DE,

EA)

Surveys

Block (IFO,

EC, Markit,

NBB, ZEW)

April

May

June

July

August

September

October

November

December

?

?

…

target variabe, but only

published with a certain delay

5

Goal of the paper


1. Data revisions

Retail Sales

(DE)

Industrial

Production

(DE)

Industrial

Production

(EA)


EA)

Surveys

Block (IFO,

EC, Markit,

NBB, ZEW)

April

May

June

July

August first estimate first estimate first estimate

September

October

November

December

flash flash

?

?

…

6

Goal of the paper


1. Data revisions

2. Release schedule (ragged-edge)

Retail Sales

(DE)

Industrial

Production

(DE)

Industrial

Production

(EA)


EA)

Surveys

Block (IFO,

EC, Markit,

NBB, ZEW)

April

May

June

July

August first estimate first estimate first estimate

September

October

November

December

flash flash

?

?

…

7

Goal of the paper


1. Data revisions

2. Release schedule (ragged-edge), which changes depending on when you

update your series

… Retail Sales

(DE)

Industrial

Production

(DE)

Industrial

Production

(EA)


EA)

Surveys

Block (IFO,

EC, Markit,

NBB, ZEW)

April

May

June

July

August

September new data new data new data

October

November new data

December

flash

yh?

8

Goal of the paper: mapping of news into forecasting

updates


► Data releases incorporate news: what is the weight of each piece of

news in the forecasts of GDP?

Retail Sales

(DE)

Industrial

Production

(DE)

Industrial

Production

(EA)


EA)

Surveys

Block (IFO,

EC, Markit,

NBB, ZEW)

April

May

June

July

August

September new data new data new data

October

November new data

December

flash

yh?

…

ω4yh

ω5yh

9

Literature

► Lots of research since Giannone, Reichlin and Small (GRS, 2008):

Kalman filter methods to extract the signal from a potentially large

information set and update it in real time.

► Still, many papers consider oversimplistic release schedules or pretend

data revisions do not exist.

► To the best of our knowledge, we are the first ones to build time series

composed of press releases for all series (different from the use of

vintages; different from the approach by Kishor & Koening, 2009)

IPI 1 Jan 1 Feb 1 Mar 1 Apr 1 May

2000Q1 100 101 99 99 99

2000Q2 103 102 102 102

2000Q3 106 105 106

2000Q4 108 106

2001Q1 110

10

Literature

► We follow the methodology of Bańbura and Modugno (2010) : ML

estimation of a DFM à la GRS (2008) to formalize the process of

nowcasting:

decompose forecast revisions in terms of news (sample dependent)

assess the expected contribution of each piece of news at forecasting

euro area GDP

(depends on both the properties of the model and the release schedule)

► Implications for variable selection (Rünstler, 2016)

Is it possible to use our weights as an alternative method for selecting an

efficient set of predictors?

11


1. Introduction










Simple representation of the real-time dataflow

-3

-2

-1

0

1

2

3

4

5

6G

fk S

urv

ey

Ha

rd d

ata

IT

Su

rve

y b

lock

Fla

sh G

DP

BE

Se

ntix S

urv

ey

Ha

rd b

lock

Fla

sh G

DP

fo

reca

st E

A

Fla

sh G

DP

EA

/DE

Gfk

Su

rve

y

Ha

rd d

ata

IT

Su

rve

y b

lock

Se

ntix S

urv

ey

Ha

rd b

lock

Gfk

Su

rve

y

Ha

rd d

ata

IT

Su

rve

y b

lock

Se

ntix S

urv

ey

Ha

rd b

lock

Gfk

Su

rve

y

Hard

data

IT

Su

rve

y b

lock

Fla

sh G

DP

BE

Se

ntix s

urv

ey

Hard

blo

ck

Fla

sh G

DP

fo

reca

st E

A

Fla

sh G

DP

EA

/DE

Reference period Publication date

July

Aug.

Sep.

Oct.

Nov.

Dec.

June

May

April

news2.0

14/08/15 news3

01/09/15

news4

16/09/15

news5

01/10/15

news6

16/10/15

news7

01/11/15

news8.0

12/11/15

new

s8.1

13/1

1/1

5

new

s8.2

15/1

1/1

5

new

s2.1

15/0

8/1

5

news1

01/08/15

13

Mapping of news into forecasting updates

► News = actual (published) figure for variable 𝑦 minus the expected value,

conditional on the previous information set

► This definition implies that news cannot be read if we do not have a prior

expectation

► The vector of news (𝐼𝑣+1) can be large, specially if a given release

incorporates historical data revisions

ℱ𝑣+1 𝑟𝑒𝑓𝑟𝑒𝑠ℎ𝑒𝑑

− ℱ𝑣 𝑎𝑟𝑐ℎ𝑖𝑒𝑣𝑒𝑑/𝑜𝑙𝑑

≡ 𝐼𝑣+1 =

y(𝑖,𝑡)1 − E y(𝑖,𝑡)1 ℱ𝑣…

y(𝑖,𝑡)J − E y(𝑖,𝑡)𝐽 ℱ𝑣

14

Quantifying the role of the news

► When updating the nowcasts, the weight of the news depends on

● the quality of the indicator (i.e. the correlation of the factor with the innovations)

● its timeliness (variables that come first will typically have a bigger weight)

[w1𝑘,𝑡 , … , w5

𝑘,𝑡 ] = E[yk,t Iv+1′ ] 𝐸 𝐼𝑣+1 𝐼𝑣+1

′

−1

E[y𝑘,𝑡 ℱ𝑟𝑒𝑓𝑟𝑒𝑠ℎ𝑒𝑑 − E[y𝑘,𝑡 ℱ𝑜𝑙𝑑 = w𝑗𝑘,𝑡 y(𝑖,𝑡)𝑗 − E y(𝑖,𝑡)𝑗 ℱ𝑜𝑙𝑑

𝐽

𝑗=1

timeliness

quality

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)

Sentix Investor confidence EA

GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE

Industrial production DE

Industrial production EA

ZEW Survey Expectations DE

ZEW Survey Current Situation DE

IFO - Expectations DE

IFO - Business Climate DE

GfK Consumer Confidence DE

Consumer Confidence BE

Business Confidence BE

ZEW Survey Expectations EA

Markit Manufacturing PMI EA

Economic confidence EA

Consumer Confidence EA

Business Climate Indicator EA

EA GDP Q3 (subsequent vintages in %)

Revision

The process of updating nowcasts

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

net impact = revision to nowcast

impacts of the news

revision to nowcast

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision


-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4S

tart

ing p

oin

t: 1

7/0

7/2

01

5

NE

WS

1: 0

1/0

8/2

015

NE

WS

2.0

: 1

6/0

8/2

01

5

NE

WS

2.1

: 16/0

8/2

015

NE

WS

2.2

: 1

6/0

8/2

01

5

NE

WS

3: 0

1/0

9/2

01

5

NE

WS

4: 1

6/0

9/2

01

5

NE

WS

5: 0

1/1

0/2

01

5

NE

WS

6: 1

6/1

0/2

01

5

NE

WS

7: 0

1/1

1/2

01

5

NE

WS

8.0

: 1

5/1

1/2

01

5

NE

WS

8.1

: 1

5/1

1/2

01

5

NE

WS

8.2

: 1

5/1

1/2

01

5

EA GDP(0)

DE GDP(0)

EA Forecast GDP(0)


GDP BE (rev +1Q)

GDP BE (0)

Retail sales DE
















Revision


GDP flash

2015Q3 publication

18

Quantifying the role of the news

► When updating the nowcasts, the weight of the news depends on

● the quality of the indicator (i.e. the correlation of the factor with the innovations)

● its timeliness (variables that come first will typically have a bigger weight)

[w1𝑘,𝑡 , … , w5

𝑘,𝑡 ] = E[yk,t Iv+1′ ] 𝐸 𝐼𝑣+1 𝐼𝑣+1

′

−1

E[y𝑘,𝑡 ℱ𝑟𝑒𝑓𝑟𝑒𝑠ℎ𝑒𝑑 − E[y𝑘,𝑡 ℱ𝑜𝑙𝑑 = w𝑗𝑘,𝑡 y(𝑖,𝑡)𝑗 − E y(𝑖,𝑡)𝑗 ℱ𝑜𝑙𝑑

𝐽

𝑗=1

timeliness

quality

► By multiplying the weights by the standard deviation of the news

associated with each data release (instead of a given realization of the

news), we obtain the standard impact of news :

● this measure allows us to compare the average informative content of the

different indicators when the object of interest is quarterly growth…

● and hence, allows us to provide a ranking of indicators

19

Empirical results

► Standard impact of macroeconomic releases in our real-time set-

up (benchmark scenario)

• Results are hard to read because of the complexity of the dataflow:

Figure 1 is just for illustration

• Results can be generalized to other quarters as well, as long as the

order of the data releases/blocks remains unchanged

-0.04

-0.02

0.00

0.02

0.04

0.06

0.08

0.10ZE

W S

urv

ey C

urr

ent

Situ

atio

n D

E

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Flas

h G

DP

BE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

Flas

h G

DP

fo

reca

st E

A

Flas

h G

DP

EA

Flas

h G

DP

DE

ZEW

Su

rvey

Cu

rren

t Si

tuat

ion

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

ZEW

Su

rvey

Cu

rren

t Si

tuat

ion

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

ZEW

Su

rvey

Cu

rren

t Si

tuat

ion

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Flas

h G

DP

BE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

Flas

h G

DP

fo

reca

st E

A

Flas

h G

DP

EA

Flas

h G

DP

DE

Standard Impact on Q3

news 1 01/08/2015 news 2.0 16/08/2015 n

ew

s 2.

1

ne

ws

2.2

news 3 01/09/2015 news 4 16/09/2015

news 5 01/10/2015 news 6 16/10/2015

news 7 01/11/2015 news 8 15/11/2015 n

ew

s 8.

1

ne

ws

8.2

-0.04

-0.02

0.00

0.02

0.04

0.06

0.08

0.10ZE

W S

urv

ey C

urr

ent

Situ

atio

n D

E

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Flas

h G

DP

BE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

Flas

h G

DP

fo

reca

st E

A

Flas

h G

DP

EA

Flas

h G

DP

DE

ZEW

Su

rvey

Cu

rren

t Si

tuat

ion

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

ZEW

Su

rvey

Cu

rren

t Si

tuat

ion

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

ZEW

Su

rvey

Cu

rren

t Si

tuat

ion

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

DE

ZEW

Su

rvey

Exp

ecta

tio

ns

EA

Co

nsu

mer

Co

nfi

den

ce B

E

Mar

kit

Man

ufa

ctu

rin

g P

MI E

A

Bu

sin

ess

Co

nfi

den

ce B

E

IFO

- B

usi

nes

s C

limat

e D

E

IFO

- C

urr

ent

Ass

essm

ent

DE

IFO

- E

xpec

tati

on

s D

E

GfK

Co

nsu

mer

Con

fide

nce

DE

Ret

ail s

ales

IT

Ind

ust

rial

pro

du

ctio

n IT

Bu

sin

ess

Clim

ate

Ind

icat

or

EA

Co

nsu

mer

Co

nfi

den

ce E

A

Eco

no

mic

co

nfi

den

ce E

A

Co

nsu

mer

Sp

end

ing

FR

Ret

ail s

ales

DE

Flas

h G

DP

BE

Fact

ory

Ord

ers

DE

Ind

ust

rial

Pro

du

ctio

n D

E

Sen

tix

Inve

sto

r co

nfi

den

ce E

A

Ind

ust

rial

Pro

du

ctio

n F

R

Ind

ust

rial

Pro

du

ctio

n E

A

Flas

h G

DP

fo

reca

st E

A

Flas

h G

DP

EA

Flas

h G

DP

DE

Standard Impact on Q3 Standard Impact on Q4

news 1 01/08/2015 news 2.0 16/08/2015 n

ew

s 2.

1

ne

ws

2.2

news 3 01/09/2015 news 4 16/09/2015

news 5 01/10/2015 news 6 16/10/2015

news 7 01/11/2015 news 8 15/11/2015 n

ew

s 8.

1

ne

ws

8.2

22

Ranking for euro area GDP flash, based on the standard

impact in the benchmark case

► Cumulative impact of data releases over a whole semester

► Confirms the dominance of soft data, but industrial production in the

euro area and Germany should not be neglected

► Notice relevance of NBB survey for EA growth prediction

0.00

0.05

0.10

0.15

0.20

0.25

0.30

0.35

23


1. Introduction










24

Counterfactual scenario’s

Analysis Objective Details Results

Benchmark Impact on euro area flash GDP Real-time dataflow Slide 19-22

Scenario 1 Counterfactual impact on euro

area flash GDP

Hard data published

without any delay Slide 25

Scenario 2

Counterfactual impact on euro

area revised GDP of the

pseudo real-time case

Hard data is fully revised

but published as in real-

time exercise

Slide 26

Scenario 3

Counterfactual impact of

revised hard data on euro area

revised GDP

Hard data is fully revised

and published without

any delay

Slide 27

For other robustness scenario’s (e.g. impact on German flash GDP), cf. paper

25

0.0

0.1

0.2

0.3

0.4

0.5

0.6

Benchmark case

0.0

0.1

0.2

0.3

0.4

0.5

0.6

Benchmark case Scenario 1

How does the impact change when we ignore the release

schedule? Scenario 1

► Hard indicators are assumed to be published at the end of the reference

month (i.e. no publication delay)

26

0.0

0.1

0.2

0.3

0.4

0.5

0.6

Benchmark case

0.0

0.1

0.2

0.3

0.4

0.5

0.6


How does the impact change when we ignore the presence

of data revisions? Scenario 2

► Hard data are revised, but treated as real-time data (i.e their publication

delay is the same as in the benchmark case)

► This represents the pseudo real-time case

27

0.0

0.1

0.2

0.3

0.4

0.5

0.6

Benchmark case

0.0

0.1

0.2

0.3

0.4

0.5

0.6


How does the impact change when the data calendar

changes and we ignore the presence of data revisions? Scenario 3

► Month-on-month growth rates of hard data were replaced by the most recent

data found via Thomson Reuters Datastream and considered revised

► Hard indicators are assumed to be published at the end of the reference month

28


1. Introduction










29

Could this ranking serve as a tool to select variables?

Yes…

► … according to some recent studies, e.g. Rünstler (2016)

● his analysis is performed in the pseudo real-time environment ≈ our scenario 2

● we construct a “small” DFM, which contains only the best-ranked indicators

from slide 42

● our results seem to confirm Rünstler’s finding

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

-100

-96

-92

-88

-84

-80

-76

-72

-68

-64

-60

-56

-52

-48

-44

-40

-36

-32

-28

-24

-20

-16

-12 -8 -4 0 4 8

12

16

20

24

28

32

36

40

RMSE of the small DFM

RMSE of the normal DFM

Comparison of the RMSE for revised EA GDP of the normal DFM and the small DFM

30

… but not in a genuine real-time environment

► If we go back to the benchmark case and construct a small model, the

smaller model does not necessarily give better results

● relying on a limited set of indicators (even those with the most informative

content) proves to be somewhat more risky in a genuine real-time environment

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

-100

-96

-92

-88

-84

-80

-76

-72

-68

-64

-60

-56

-52

-48

-44

-40

-36

-32

-28

-24

-20

-16

-12 -8 -4 0 4 8

12

16

20

24

28

32

36

40

44

RMSE of the small DFM

RMSE of the normal DFM

Comparison of the RMSE for flash EA GDP of the normal DFM and the small DFM

31


1. Introduction










32

Which news blocks turned out to significantly improve the

RMSE?

0.0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

0.0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1.0

-100

-97

-94

-91

-88

-85

-82

-79

-76

-73

-70

-67

-64

-61

-58

-55

-52

-49

-46

-43

-40

-37

-34

-31

-28

-25

-22

-19

-16

-13

-10 -7 -4 -1 2 5 8

11

14

17

20

23

26

29

32

35

38

41

44

RMSE DFM4 (endof news block)

RMSE DFM4 with3 lags

Ne

ws1

**

Ne

ws2

Ne

ws3

**

Ne

ws4

*

Ne

ws5

*

Ne

ws6

Ne

ws7

**

Ne

ws8

Ne

ws8

.1**

*

***, ** and * demonstrate significance at the 5%, 20% and 20% level respectively, using the fixed-smoothing (FS) asymptotics, as proposed by Coroneo

and Iacone (2016). Evaluation sample: 2007Q1 – 2015Q1.

33

What about the performance of our model relative to

others? Some visual investigation…

-3.0

-2.5

-2.0

-1.5

-1.0

-0.5

0.0

0.5

1.0

1.5

200

7 Q

1

200

7 Q

3

200

8 Q

1

200

8 Q

3

200

9 Q

1

200

9 Q

3

2010 Q

1

201

0 Q

3

201

1 Q

1

201

1 Q

3

201

2 Q

1

201

2 Q

3

2013 Q

1

201

3 Q

3

201

4 Q

1

201

4 Q

3

201

5 Q

1

201

5 Q

3

EA flash GDP DFM4 (h = 30 days) Bloomberg (h = 44 days)

Euro area flash GDP and our nowcasts compared to the Bloomberg forecast

34

What about the performance of our model relative to

others? Some formal investigation…

► Relative RMSE should be < 1

● generally OK, although not statistically significant

► Null hypothesis of the encompassing test: one of the forecasts

encompasses all the relevant information from the other

● H0 rejected in all cases: our DFM nowcast can be improved by combining it

with the other benchmark… but also the other way around!

Models Horizon Relative

RMSE

Encompassing test

DFM enc BM BM enc DFM

DFM

Now-Casting.com 0 days 1.31 0.43*** 0.33**

DFM

Now-Casting.com 44 days 0.70* 0.28*** 0.56***

DFM

PMI indicator 0 days 0.83 0.31** 0.68**

DFM

Bloomberg 44 days

1.13 0.60*** 0.37*

***, ** and * demonstrate significance at the 5%, 10% and 20% level respectively, using the fixed-smoothing (FS) asymptotics, as proposed by Coroneo

and Iacone (2016). Evaluation sample: 2011Q3 – 2015Q1.

35


1. Introduction










36

Concluding remarks

► Our paper demonstrates the importance of survey data for GDP

nowcasts, EVEN IF hard data were available without any publication

delay…

► … and even for final GDP (which is supposedly constructed using

information from hard data only)

► The paper highlights the importance of using real-time information. We

show that the alternative pseudo real-time case delivers significantly

different results and can lead to doubtful interpretations when it comes to

(the benefit of) variable selection

► FYI: you can reproduce the results by using JDemetra+ software1 and the

nowcasting plugin

1 JDemetra+ is free and open source software written in Java. Download it here: https://github.com/jdemetra/jdemetra-app/releases/tag/v2.1.0-rc2.

The Nowcasting plugin should be downloaded here: https://github.com/nbbrd/jdemetra-nowcasting/releases. After downloading it, go to the Tools option in

JDemetra+ and select plugins. The sofware is portable and it could even be executed from a USB disc.

https://github.com/jdemetra/jdemetra-app/releases/tag/v2.1.0-rc2







https://github.com/nbbrd/jdemetra-nowcasting/releases





Thank you!

Any questions or comments?

Back-up slides

39

Statistical significance of each update based on fixed-

smoothing asymptotics

Given the small size of our evaluation sample and the time-series correlation patterns, we determine signicance at

the 5% (dark grey),10% and 20% (light grey) level using the fixed-smoothing (FS) asymptotics, as proposed by

Coroneo and Iacone (2016).

nowcasting real economic activity in the euro area · 2016-11-18 · nbp warsaw workshop on...

Documents