TURKISH STATISTICAL INSTITUTE TurkStat Difficulties in Seasonal Adjustment N. Alpay KOÇAK Turkish Statistical Institute UNECE Workshop on Seasonal Adjustment 20 – 23 February 2012, Ankara, Turkey 05.11.2015

Download Report

Transcript TURKISH STATISTICAL INSTITUTE TurkStat Difficulties in Seasonal Adjustment N. Alpay KOÇAK Turkish Statistical Institute UNECE Workshop on Seasonal Adjustment 20 – 23 February 2012, Ankara, Turkey 05.11.2015

TURKISH STATISTICAL INSTITUTE
TurkStat
Difficulties in
Seasonal Adjustment
N. Alpay KOÇAK
Turkish Statistical Institute
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
1
TURKISH STATISTICAL INSTITUTE
TurkStat
Difficulties in seasonal adjustment
• In general manner, seasonal adjusment is
a type of economic time series analysis .
• Trend-Cycle, Seasonal, Transitory,
Irregular, Calendar Effect, Outliers,
Missing Observations, Forecasts etc.
• Actually, one can use one of these
components to interprete the properties of
the economic time series.
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
2
TURKISH STATISTICAL INSTITUTE
TurkStat
Difficulties in seasonal adjustment
• Original series – seasonality = Seasonal
Adjusted series (for short term economic
analysis)
• Trend-cycle component (for short-term economic
analysis with smoother series)
• Seasonal and calendar component (to
understand underlying movements of the series
in a year)
• Outliers (to understand shocks and persistent
effects on the series)
• Etc...
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
3
TURKISH STATISTICAL INSTITUTE
TurkStat
Classical Output of Demetra+
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
4
TurkStat
TURKISH STATISTICAL INSTITUTE
Trend_Cycle = Trend + Cycle
TREND
1,100,000
TREND_CYCLE
1,000,000
1,100,000
900,000
800,000
1,000,000
700,000
600,000
900,000
500,000
00
01
02
03
04
05
06
07
08
09
10
09
10
800,000
CYCLE
40,000
700,000
30,000
600,000
20,000
10,000
500,000
00
01
02
03
04
05
06
07
08
09
10
0
-10,000
-20,000
00
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
01
02
03
04
05
06
07
08
05.11.2015
5
TurkStat
TURKISH STATISTICAL INSTITUTE
Seasonal Component
SEASONAL
SEASONAL by Quarter
1.2
1.2
1.1
1.1
1.0
1.0
0.9
0.9
0.8
0.8
0.7
0.7
0.6
Q1
Q2
Q3
Q4
Means by Quarter
0.6
00
01
02
03
04
05
06
07
08
09
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
10
05.11.2015
6
TurkStat
TURKISH STATISTICAL INSTITUTE
Irregular component
IRREGULAR
1.016
1.012
1.008
1.004
1.000
0.996
0.992
0.988
00
01
02
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
03
04
05
06
07
08
09
10
05.11.2015
7
TurkStat
TURKISH STATISTICAL INSTITUTE
Trading Days
(Fixed holidays included))
Trading days
Parameter
Value
Monday
-0.0187
Tuesday
0.0007
Wednesday
-0.0103
Thursday
0.0286
Friday
-0.0126
Saturday
0.0050
Sunday(derived)0.0072
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
Std error
0.0105
0.0097
0.0111
0.0097
0.0106
0.0103
0.0091
T-Stat
-1.77
0.07
-0.93
2.94
-1.19
0.49
0.79
P-value
0.0861
0.9447
0.3611
0.0061
0.2424
0.6309
0.4334
05.11.2015
8
TURKISH STATISTICAL INSTITUTE
TurkStat
Difficulties in seasonal adjustment
• Two main requests for performing good
seasonal adjustment of a time series
– Conceptual knowledge
– Statistical and Econometric knowledge
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
9
TURKISH STATISTICAL INSTITUTE
TurkStat
Difficulties in seasonal adjustment
• Conceptual knowledge
– Analytical Framework, Concepts, Definitions, and
Classifications
• Definition
• Classification
– Scope of the data
• Methodologic issues
• Geographical issues
– Accounting Conventions
• Unit
• Valuation
– Compilation Practices
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
10
TURKISH STATISTICAL INSTITUTE
TurkStat
Statistical and Econometric
knowledge
•
•
•
•
•
•
Basic data transformations
Model estimation (ARIMA model)
Significancy
Diagnostics
Spectrum graphics
Filters
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
05.11.2015
11
TurkStat
TURKISH STATISTICAL INSTITUTE
Transformation: Level & Log
14
1100000
13.9
1000000
13.8
900000
13.7
13.6
800000
13.5
700000
13.4
600000
13.3
13.2
500000
1
3
5
7
9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43
LOG_TREND
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
TREND
05.11.2015
12
TURKISH STATISTICAL INSTITUTE
TurkStat
Statistical and Econometric
knowledge
•
•
•
•
•
•
Basic data transformations
Model estimation (ARIMA model)
Significancy
Diagnostics
Spectrum graphics
Filters
UNECE Workshop on Seasonal Adjustment
20 – 23 February 2012, Ankara, Turkey
Not so much
theoretical
detail!
Just to know
Why and what
they do?
05.11.2015
13