Transcript Template for Structural Economic Statistics

WORKING PARTY ON NATIONAL ACCOUNTS
Paris, 3-5 October 2007
Revisions in Quarterly GDP of OECD
Countries: An Update
Document STD/CSTAT/WPNA(2007)15
Richard McKenzie
The OECD Real-Time Data and
Revisions Analysis Database
• Full time series of data published every month
starting from the February 1999 edition of the Main
Economic Indicators for 21 key economic variables
• Access OECD revisions analysis studies for GDP,
Index of Industrial Production and Retail Trade
Volume
• Automated programs and detailed user guide
allowing users to perform their own revisions analysis
for any country / variable combination available in
the database
• Enables economists to test the performance of their
econometric models in simulated real-time (out-ofsample testing using original first release data)
http://stats.oecd.org/mei/default.asp?rev=1
Update of Quarterly GDP
Revisions Analysis
• Work done since the presentation at the last meeting:
– Added data up to June 2007 edition of the MEI
– Revisions analysis extended to reference periods
1994Q4: 2006Q3 (last year: 1995Q1:2004Q4)
– Assessment of revisions after 5 months, to capture
first revision
– Assessment of revision to year-on-year (YoY)
growth rates (i.e. 4 quarter rate of change) to
complement existing quarter-on-previous quarter
(QoQ) growth rates
– Results presented in OECD Statistics Working
Papers and at various conferences
Results
• Extra one years worth of data doesn’t change things
much as the average is over 12 years now
– Revisions to first published QoQ growth rates after
one year, Finland up a bit ; Norway, Portugal and
Korea down
• Lets focus on the new measures added to the database:
size of first revision, revision to YoY growth rates,
statistical significance of mean revision at different
intervals
First revision to quarterly GDP: Relative mean absolute revision
to
QoQ and YoY growth rates
0.50
QoQ
YoY
RMAR
0.40
0.30
0.20
0.10
0.00
AUS BEL CAN CHE DEU DNK ESP FIN FRA GBR ITA JPN KOR NLD NOR NZL PRT USA
Statistical significance of the mean revision at different intervals
Y1_P
Country
AUS
BEL
CAN
CHE
DEU
DNK
ESP
FIN
FRA
GBR
ITA
JPN
KOR
NLD
NOR
NZL
PRT
USA
Average
QoQ
-0.004
0.05
-0.01
-0.002
-0.02
0.13 **
0.01
0.16 **
0.01
0.04
0.001
-0.04
-0.01
0.05
0.01
0.03
-0.04
0.05
0.02
L_P
YoY
0.13
0.07
0.09
0.07
-0.03
0.19
0.12
0.50
0.13
0.09
0.001
-0.13
0.08
0.25
0.24
0.13
0.06
-0.002
0.11
QoQ
*
**
**
*
*
**
**
0.07
0.07
0.12
0.07
0.01
0.21
0.16
0.15
0.05
0.17
0.07
0.06
0.13
0.14
0.15
0.27
0.14
-0.01
0.11
**
**
**
***
*
**
L_Y1
YoY
QoQ
0.24
0.07
0.47
0.39
-0.03
0.16
0.70
0.53
0.23
0.59
0.17
0.19
0.35
0.64
0.74
0.91
0.65
-0.02
0.39
0.10
0.02
0.13
0.10
0.02
0.06
0.16
0.03
0.02
0.11
0.07
0.08
0.13
0.13
0.13
0.20
0.23
-0.04
0.09
**
**
***
**
*
***
**
***
***
***
YoY
**
**
**
**
*
*
*
0.17
0.02
0.40
0.36
0.01
-0.11
0.61
0.19
0.01
0.45
0.16
0.23
0.18
0.55
0.47
0.73
0.64
-0.03
0.28
**
**
***
**
*
**
**
***
Issues for discussion
• New OECD database interface enabling revisions
analysis for components of GDP and other
variables
• Statistical significance of positive mean revision at
longer revision intervals for QoQ growth rates
– Could this reflect a tendency from the impact of
methodological changes? If so, how do we
communicate this to users who think there may
be a bias?
• Statistical significance of positive mean revision to
YoY growth rates, should we be concerned about
these, is more work needed?