Professional Documents
Culture Documents
AND
TIME SERIES
PRODUCTION OF
STEEL
1996
60
1997
72
1998
75
1999
65
2000
80
2001
85
2002
95
YEAR
1996
1997
1998
1990
2000
2001
2002
TIME PRODUCTI
SCALE
ON (Y)
(X)
1
2
3
4
5
6
7
60
72
75
65
80
85
95
XY
Exponential Smoothing
Method
It is a type of moving average
forecasting technique
It weighs past data from previous
time periods with exponentially
decreasing importance in the
forecast so that the recent data
carries more weight
Exponential Smoothing
Method
Example
A firm uses simple exponential
smoothing with =0.1 to forecast
demand. The forecast for the week of
Feb 1 was 500 units, whereas actual
demand was 450 units.
(a) Forecast demand for week of Feb
8?
Example
A firm uses simple exponential
smoothing with =0.1 to forecast
demand. The forecast for the week of
Feb 1 was 500 units, whereas actual
demand was 450 units.
(a) Forecast demand for week of Feb
8
Solution
F(t+1) = 500 + 0.1(450-500) = 495
units
MEASUREMENT OF SEASONAL
EFFECTS
Seasonal effects arise as the result of
changes in the seasons during the
year or may result due to habits ,
customs , or festival that occur at the
same time year after year
We have three main reasons to study
seasonal effects
1. The description of seasonal effect
provides a better understanding of the
impact this component has upon a
particular time series
MEASUREMENT OF SEASONAL
EFFECTS
2. Once the seasonal pattern that exists is
established, seasonal effect can be eliminated
from the time series in order to observe the effect
of the other components, such as cyclical and
irregular components. Elimination of seasonal
effect from the series is referred to as
deasonalising or seasonal adjusting
3. Trend analysis may be adequate for long range
forecast , but for short run predictions, knowledge
of seasonal effects on time series data is essential
for projection of past pattern into the future
MEASUREMENT OF SEASONAL
EFFECTS
Seasonal Index
Are measured in terms of an index,
called seasonal index, attached to
each period of time series within a
year
If monthly data are considered, there
are 12 separate indexes of each
month
Similarly for quarterly data there are
4 separate indexes for each quarter
Example
The data on prices (Rs in per kg) of a
certain commodity during 2000 to
2004 are shown below.
Calculate the seasonal indexes by the
average percentage method (SIMPLE
AVERAGES METHOD) and obtain deseasonalized values
Example
Year
2000
2001
2002
2003
2004
Quart
er 1
45
48
49
52
60
Quart
er 2
54
56
63
65
70
Quart
er 3
72
63
70
75
84
Quart
er 4
60
56
65
72
66
Example
Year
Quarter
1
2000
45
2001
48
2002
49
2003
52
2004
60
Quarterl 254
y
Total
Quarterl
y
Average
Quarter
2
54
56
63
65
70
308
Quarter
3
72
63
70
75
84
364
Quarter
4
60
56
65
72
66
319
Example
Year
2000
2001
2002
2003
2004
Quarte
rly
Total
Quarte
rly
Averag
e
Quarter 1
45
48
49
52
60
254
(45+48+4
9+52+60)
50.8
(254/5=50
.8)
Q2
54
56
63
65
70
308
Q 3
72
63
70
75
84
364
Q4
60
56
65
72
66
319
61.6
72.8
63.8
Example
Example
Year
Quarter
1
2000
45
2001
48
2002
49
2003
52
2004
60
Quarter 254
ly
Total
Quarter 50.8
ly
Average
Quarter
2
54
56
63
65
70
308
Quarter
3
72
63
70
75
84
364
Quarter
4
60
56
65
72
66
319
61.6
72.8
63.8
Example
Deasonalized Values
Seasonalized influences are
removed from a time series data by
dividing the actual y value for each
quarter by its corresponding
seasonal index
Deseasonalized value =[ actual
quarterly value/seasonal index of
corresponding quarter] x 100
Example
DESEASONALIZED
2000
2001
2002
2003
2004
Quarter
1
55.14
(45/81.6
0) x 100
58.82
60.09
63.72
73.52
VALUES
56.59
63.66
65.68
70.74
53.87
59.85
64.13
71.83
54.64
63.42
70.25
64.40
THANK YOU