Exponential Smoothing with Trend
• As we move toward medium-range
forecasts, trend becomes more important.
• Incorporating a trend component into
exponentially smoothed forecasts is called double exponential smoothing.
– The estimate for the average and the estimate
for the trend are both smoothed.
Exponential Smoothing with Trend Adjustment
Forecast including trend (FIT
t)OR Adjusted Forecast (AF
t) = exponentially smoothed forecast (F
t) + exponentially smoothed trend (T
t)
That is, AF
t= F
t+ T
tWe need to compute both Ft and Tt
F
t= Last period’s forecast
+ D (Last period’s actual –Last period’s forecast) F
t= F
t-1+ D (A
t-1–F
t-1)
or
T
t= E(This period’s Forecast - last period’s Forecast) + (1- E) (Trend estimate last period)
T
t= E(F
t- F
t-1) + (1- E) T
t-1for all t
or
Exponential Smoothing with Trend Adjustment – (contd.)
F
t= exponentially smoothed forecast of the data series in period t T
t= exponentially smoothed trend in period t
A
t= actual demand in period t
α = smoothing constant for the average
β = smoothing constant for the trend
Adjusted Exponential Smoothing Example
PERIOD MONTH DEMAND
1 Jan 37
2 Feb 40
3 Mar 41
4 Apr 37
5 May 45
6 Jun 50
7 Jul 43
8 Aug 47
9 Sep 56
10 Oct 52
11 Nov 55
12 Dec 54
Adjusted Exponential Smoothing Example
Per Month Dem Ft+1 Tt+1 AFt+1
1 Jan 37 37.00 - -
2 Feb 40 37.00 0.00 37.00
3 Mar 41 38.50 0.45 38.95
4 Apr 37 39.75 0.69 40.44
5 May 45 38.37 0.07 38.44
6 Jun 50 41.68 1.04 42.73
7 Jul 43 45.84 1.97 47.82
8 Aug 47 44.42 0.95 45.37
9 Sep 56 45.71 1.05 46.76
10 Oct 52 50.85 2.28 58.13
11 Nov 55 51.42 1.76 53.19
12 Dec 54 53.21 1.77 54.98
13 Jan - 53.61 1.36 54.96
F3=F2+0.50(A2-F2) = 37+0.50*3 = 38.5 T3 = E(F3 - F2) + (1 - E) T2
= (0.30)(38.5 - 37.0) + (0.70)(0)
= 0.45
AF3 = F3 + T3
=38.5 + 0.45 = 38.95 T13 = E(F13 - F12) + (1 - E) T12
=(0.30)(53.61 - 53.21) + (0.70)(1.77)
=1.36
AF13 = F13 + T13 = 53.61 + 1.36 = 54.96
Forecast ( D = 0.50)
Adjusted Exponential Smoothing Forecasts
70 – 60 – 50 – 40 – 30 – 20 – 10 –
0 – | | | | | | | | | | | | |
1 2 3 4 5 6 7 8 9 10 11 12 13
Adjusted forecast (D = 0.50; E = 0.30)) Actual
Demand
Period
Forecast (D = 0.50)
Seasonal Adjustments
i i
S D D
Seasonal factor = = ∑
• Repetitive increase/decrease in demand
– Use seasonal factor to adjust forecast
Where
D
iis the sum of demands of the period i in the time series data
6Dis net sum of demands of the entire period in the time series data
Example: Seasonal Adjustment [1]
Demand (1000’s per quarter)
Year 1 2 3 4 Total
2004 12.6 8.6 6.3 17.5 45.0
2005 14.1 10.3 7.5 18.2 50.1
2006 15.3 10.6 8.1 19.6 53.6
Total 42.0 29.5 21.9 55.3 148.7
Si 0.28 0.20 0.15 0.37
Computed trend line for data y = 40.97 + 4.30 X [Given to you]
2006 (year 4) forecast = 40.97 + 4.30 (4) = 58.17
Forecasted demand after seasonal adjustment for the year 2006 is
2006 16.28 11.63 8.73 21.53
--- Details
58.17 x 0.28 = 16.28; 58.17 x 0.20 = 11.63;
58.17 x 0.15 = 8.73; 58.17 x 0.37 = 21.53
---
1 1 42 0
148 7 0 28
S D
= D = =
∑
.. .SF
1= (S
1) (F
5)
= (0.28)(58.17) = 16.28 SF
2= (S
2) (F
5)
= (0.20)(58.17) = 11.63 SF
3= (S
3) (F
5)
= (0.15)(58.17) = 8.73 SF
4= (S
4) (F
5)
= (0.37)(58.17) = 21.53
Quarter Year 1 Year 2 Year 3 Year 4
1 45 70 100 100
2 335 370 585 725
3 520 590 830 1160
4 100 170 285 215
Total 1000 1200 1800 2200
Average 250 300 450 550
Example: Seasonal Adjustment [2]
Quarter Year 1 Year 2 Year 3 Year 4
1 45 70 100 100
2 335 370 585 725
3 520 590 830 1160
4 100 170 285 215
Total 1000 1200 1800 2200
Average 250 300 450 550
Seasonal Index = Actual Demand Average Demand
Example: Seasonal Adjustment [2]
Quarter Year 1 Year 2 Year 3 Year 4
1 45 70 100 100
2 335 370 585 725
3 520 590 830 1160
4 100 170 285 215
Total 1000 1200 1800 2200
Average 250 300 450 550
Seasonal Index = = 0.18 45 250
Example: Seasonal Adjustment [2]
Quarter Year 1 Year 2 Year 3 Year 4
1 45/250 = 0.18 70 100 100
2 335 370 585 725
3 520 590 830 1160
4 100 170 285 215
Total 1000 1200 1800 2200
Average 250 300 450 550
Seasonal Index = = 0.18 45 250
Example: Seasonal Adjustment [2] – Contd.
Quarter Year 1 Year 2 Year 3 Year 4 1 45/250 = 0.18 70/300 = 0.23 100/450 = 0.22 100/550 = 0.18 2 335/250 = 1.34 370/300 = 1.23 585/450 = 1.30 725/550 = 1.32 3 520/250 = 2.08 590/300 = 1.97 830/450 = 1.84 1160/550 = 2.11 4 100/250 = 0.40 170/300 = 0.57 285/450 = 0.63 215/550 = 0.39
Example: Seasonal Adjustment [2] – Contd.
Quarter Year 1 Year 2 Year 3 Year 4 1 45/250 = 0.18 70/300 = 0.23 100/450 = 0.22 100/550 = 0.18 2 335/250 = 1.34 370/300 = 1.23 585/450 = 1.30 725/550 = 1.32 3 520/250 = 2.08 590/300 = 1.97 830/450 = 1.84 1160/550 = 2.11 4 100/250 = 0.40 170/300 = 0.57 285/450 = 0.63 215/550 = 0.39
Quarter Average Seasonal Index
1 (0.18 + 0.23 + 0.22 + 0.18)/4 = 0.20 2 3
4
Example: Seasonal Adjustment [2] – Contd.
Quarter Year 1 Year 2 Year 3 Year 4 1 45/250 = 0.18 70/300 = 0.23 100/450 = 0.22 100/550 = 0.18 2 335/250 = 1.34 370/300 = 1.23 585/450 = 1.30 725/550 = 1.32 3 520/250 = 2.08 590/300 = 1.97 830/450 = 1.84 1160/550 = 2.11 4 100/250 = 0.40 170/300 = 0.57 285/450 = 0.63 215/550 = 0.39
Quarter Average Seasonal Index
1 (0.18 + 0.23 + 0.22 + 0.18)/4 = 0.20 2 (1.34 + 1.23 + 1.30 + 1.32)/4 = 1.30 3 (2.08 + 1.97 + 1.84 + 2.11)/4 = 2.00 4 (0.40 + 0.57 + 0.63 + 0.39)/4 = 0.50
Example: Seasonal Adjustment [2] – Contd.
Quarter Year 1 Year 2 Year 3 Year 4 1 45/250 = 0.18 70/300 = 0.23 100/450 = 0.22 100/550 = 0.18 2 335/250 = 1.34 370/300 = 1.23 585/450 = 1.30 725/550 = 1.32 3 520/250 = 2.08 590/300 = 1.97 830/450 = 1.84 1160/550 = 2.11 4 100/250 = 0.40 170/300 = 0.57 285/450 = 0.63 215/550 = 0.39
Quarter Average Seasonal Index Forecast 1 (0.18 + 0.23 + 0.22 + 0.18)/4 = 0.20
2 (1.34 + 1.23 + 1.30 + 1.32)/4 = 1.30 3 (2.08 + 1.97 + 1.84 + 2.11)/4 = 2.00 4 (0.40 + 0.57 + 0.63 + 0.39)/4 = 0.50
Projected Annual Demand = 2600 [Given]
Average Quarterly Demand = 2600/4 = 650
Example: Seasonal Adjustment [2] – Contd.
Quarter Year 1 Year 2 Year 3 Year 4 1 45/250 = 0.18 70/300 = 0.23 100/450 = 0.22 100/550 = 0.18 2 335/250 = 1.34 370/300 = 1.23 585/450 = 1.30 725/550 = 1.32 3 520/250 = 2.08 590/300 = 1.97 830/450 = 1.84 1160/550 = 2.11 4 100/250 = 0.40 170/300 = 0.57 285/450 = 0.63 215/550 = 0.39
Quarter Average Seasonal Index Forecast
1 (0.18 + 0.23 + 0.22 + 0.18)/4 = 0.20 650(0.20) = 130 2 (1.34 + 1.23 + 1.30 + 1.32)/4 = 1.30
3 (2.08 + 1.97 + 1.84 + 2.11)/4 = 2.00 4 (0.40 + 0.57 + 0.63 + 0.39)/4 = 0.50
Projected Annual Demand = 2600
Average Quarterly Demand = 2600/4 = 650
Example: Seasonal Adjustment [2] – Contd.
Quarter Year 1 Year 2 Year 3 Year 4 1 45/250 = 0.18 70/300 = 0.23 100/450 = 0.22 100/550 = 0.18 2 335/250 = 1.34 370/300 = 1.23 585/450 = 1.30 725/550 = 1.32 3 520/250 = 2.08 590/300 = 1.97 830/450 = 1.84 1160/550 = 2.11 4 100/250 = 0.40 170/300 = 0.57 285/450 = 0.63 215/550 = 0.39
Quarter Average Seasonal Index Forecast
1 (0.18 + 0.23 + 0.22 + 0.18)/4 = 0.20 650(0.20) = 130 2 (1.34 + 1.23 + 1.30 + 1.32)/4 = 1.30 650(1.30) = 845 3 (2.08 + 1.97 + 1.84 + 2.11)/4 = 2.00 650(2.00) = 1300 4 (0.40 + 0.57 + 0.63 + 0.39)/4 = 0.50 650(0.50) = 325
Example: Seasonal Adjustment [2] – Contd.
Seasonalised Time Series Regression Analysis
1. Select a representative historical data set.
2. Develop a seasonal index for each season.
3. Use the seasonal indexes to De-Seasonalise the data.
4. Perform linear regression analysis on the De-Seasonalised data.
5. Use the regression equation to compute the forecasts.
6. Use the seasonal indexes to reapply the seasonal patterns to the
forecasts.
Example: Computer Products Corp.
Seasonalized Times Series Regression Analysis
An analyst at CPC wants to develop next year’s
quarterly forecasts of sales revenue for CPC’s line
of Epsilon Computers. She believes that the most
recent 8 quarters of sales (shown on the next slide)
are representative of next year’s sales.
Example: Computer Products Corp.
• Seasonalised Times Series Regression Analysis – Representative Historical Data Set
Year Qtr. ($mil.) Year Qtr. ($mil.)
1 1 7.4 2 1 8.3
1 2 6.5 2 2 7.4
1 3 4.9 2 3 5.4
1 4 16.1 2 4 18.0
Example: Computer Products Corp.
– Compute the Seasonal Indexes
Quarterly Sales
Year Q1 Q2 Q3 Q4 Total
1 7.4 6.5 4.9 16.1 34.9
2 8.3 7.4 5.4 18.0 39.1
Totals 15.7 13.9 10.3 34.1 74.0 Qtr. Avg. 7.85 6.95 5.15 17.05 9.25 Seas.Ind. .849 .751 .557 1.843 4.000
7.85 / 9.25
Example: Computer Products Corp.
De-Seasonalise the Data
Quarterly Sales
Year Q1 Q2 Q3 Q4
1 8.72 8.66 8.80 8.74
2 9.78 9.85 9.69 9.77
De-Seasonalised data for Q1 = { Actual Q1 sales / Seas. Index } Time series data:
Quarterly Sales
Year Q1 Q2 Q3 Q4
1 7.4 6.5 4.9 16.1
2 8.3 7.4 5.4 18.0
Seasonal Index 0.849 0.751 0.557 1.843
Y
t= T
tx S
tx C
tx R
tAssum. There is no Ct& Rt
Y
t= T
tx S
tY
t(dese.)= (Y
t/S
t)
Example: Computer Products Corp.
– Perform Regression on De-seasonalized Data
Yr. Qtr. x y x
2xy
1 1 1 8.72 1 8.72
1 2 2 8.66 4 17.32
1 3 3 8.80 9 26.40
1 4 4 8.74 16 34.96
2 1 5 9.78 25 48.90
2 2 6 9.85 36 59.10
2 3 7 9.69 49 67.83
2 4 8 9.77 64 78.16
Totals 36 74.01 204 341.39
Y = 8.357 + 0.199X
2
204(74.01) 36(341.39 )
a 8.357
8(204) (36 )
= − =
−
28(341.39) 36(74.01)
b 0.199
8(204) (36)
= − =
−
Example: Computer Products Corp.
Y
9= 8.357 + 0.199(9) = 10.148 Y
10= 8.357 + 0.199(10) = 10.347 Y
11= 8.357 + 0.199(11) = 10.546 Y
12= 8.357 + 0.199(12) = 10.745
Note: Average sales are expected to increase by .199 million (about $200,000) per quarter.
MODEL : Y = 8.357 + 0.199X
Compute the De-Seasonalised Forecasts
Example: Computer Products Corp.
Seasonalised the Forecasts
Seas. De-seas. Seas.
Yr. Qtr. Index Forecast Forecast
3 1 .849 10.148 8.62
3 2 .751 10.347 7.77
3 3 .557 10.546 5.87
3 4 1.843 10.745 19.80
Time Series Models & Classical Decomposition
• Decomposition time series models:
• Multiplicative: Y = T x C x S x e
• Additive: Y = T + C + S + e
T = Trend component C = Cyclical component S = Seasonal component
e = Error or random component
Time Series Models & Classical Decomposition
• Classical decomposition is used to isolate trend,
seasonal, and other variability components from a
time series model
Classical Decomposition Explained
Basic Steps:
1. Determine seasonal indexes using the ratio to moving average method
2. Deseasonalize the data
3. Develop the trend-cyclical regression equation using deseasonalized data
4. Multiply the forecasted trend values by their
seasonal indexes to create a more accurate
forecast
• Start with multiplicative model…
Y = TCSe
• Then
Se = (Y/TC)
Classical Decomposition:
Illustration
• Gem Company’ s operations department has been asked to deseasonalize and forecast sales for the next four quarters of the coming year
• The Company has compiled its past sales data in Table 1
• An illustration using classical decomposition will follow
Table 1: Gem Company’s Sales Data
Original Forecasted Year Quarter Period Sales Sales
t Y TS
1 1 1 55 -
2 2 47 -
3 3 65 -
4 4 70 -
2 1 5 65 -
2 6 58 -
3 7 75 -
4 8 80 -
3 1 9 65 -
2 10 62 -
3 11 80 -
4 12 85 -
4 1 13 70 -
2 14 65 -
3 15 85 -
4 16 90 -
5 1 17 - ?
2 18 - ?
3 19 - ?
4 20 - ?
Classical Decomposition Illustration:
Step 1
• (a) Compute the four- quarter simple
moving average
Ex: simple MA at end of Qtr 2 and
beginning of Qtr 3 (55+47+65+70)/4 =
59.25
Moving Year Quarter Period Sales Average
t Y
1 1 1 55
2 2 47 59.25
3 3 65 61.75
4 4 70 64.50
2 1 5 65 67.00
2 6 58 69.50
3 7 75 69.50
4 8 80 70.50
3 1 9 65 71.75
2 10 62 73.00
3 11 80 74.25
4 12 85 75.00
4 1 13 70 76.25
2 14 65 77.50
3 15 85
4 16 90
Classical Decomposition Illustration: Step 1
• (b) Compute the two- quarter centered
moving average
Ex: centered MA at middle of Qtr 3
(59.25+61.25)/2
= 60.500
Table 2: Four-Quarter Moving Average
Simple Centered Moving Moving Year Quarter Period Sales Average Average
t Y TC
1 1 1 55
2 2 47 59.25
3 3 65 61.75 60.500
4 4 70 64.50 63.125
2 1 5 65 67.00 65.750
2 6 58 69.50 68.250
3 7 75 69.50 69.500
4 8 80 70.50 70.000
3 1 9 65 71.75 71.125
2 10 62 73.00 72.375
3 11 80 74.25 73.625
4 12 85 75.00 74.625
4 1 13 70 76.25 75.625
2 14 65 77.50 76.875
3 15 85
4 16 90
Classical Decomposition Illustration: Step 1
• (c) Compute the seasonal-error
component (percent MA)
Ex: percent MA at Qtr 3
(65/60.500)
= 1.074
Table 2: Four-Quarter Moving Average
Simple Centered Percent Moving Moving Moving Year Quarter Period Sales Average Average Average
t Y TC Se=Y/(TC)
1 1 1 55
2 2 47 59.25
3 3 65 61.75 60.500 1.074
4 4 70 64.50 63.125 1.109
2 1 5 65 67.00 65.750 0.989
2 6 58 69.50 68.250 0.850
3 7 75 69.50 69.500 1.079
4 8 80 70.50 70.000 1.143
3 1 9 65 71.75 71.125 0.914
2 10 62 73.00 72.375 0.857
3 11 80 74.25 73.625 1.087
4 12 85 75.00 74.625 1.139
4 1 13 70 76.25 75.625 0.926
2 14 65 77.50 76.875 0.846
3 15 85
4 16 90
Classical Decomposition Illustration: Step 1
• (d) Compute the unadjusted seasonal index using the seasonal- error components from Table 2
Ex (Qtr 1): [(Yr 2, Qtr 1) + (Yr 3, Qtr 1) + (Yr 4, Qtr 1)]/3
= [0.989+0.914+0.926]/3 = 0.943
Table 3: Seasonal Index Computation
Unadjusted Adjusted
Seasonal Adjusting Seasonal
Quarter Average Index Factor Index
1 (0.989+0.914+0.926)/3 = 0.943 x (4.000/4.004) = 0.942 2 (0.850+0.857+0.846)/3 = 0.851 x (4.000/4.004) = 0.850 3 (1.074+1.079+1.087)/3 = 1.080 x (4.000/4.004) = 1.079 4 (1.109+1.143+1.139)/3 = 1.130 x (4.000/4.004) = 1.129
4.004 4.000
Classical Decomposition Illustration: Step 1
• (e) Compute the adjusting factor by dividing the number of quarters (4) by the sum of all calculated unadjusted seasonal indexes
= 4.000/(0.943+0.851+1.080+1.130) = (4.000/4.004)
Table 3: Seasonal Index Computation
Unadjusted Adjusted
Seasonal Adjusting Seasonal
Quarter Average Index Factor Index
1 (0.989+0.914+0.926)/3 = 0.943 x (4.000/4.004) = 0.942 2 (0.850+0.857+0.846)/3 = 0.851 x (4.000/4.004) = 0.850 3 (1.074+1.079+1.087)/3 = 1.080 x (4.000/4.004) = 1.079 4 (1.109+1.143+1.139)/3 = 1.130 x (4.000/4.004) = 1.129
4.004 4.000
Classical Decomposition Illustration: Step 1
• (f) Compute the adjusted seasonal index by multiplying the unadjusted seasonal index by the adjusting factor
Ex (Qtr 1): 0.943 x (4.000/4.004) = 0.942
Table 3: Seasonal Index Computation
Unadjusted Adjusted
Seasonal Adjusting Seasonal
Quarter Average Index Factor Index
1 (0.989+0.914+0.926)/3 = 0.943 x (4.000/4.004) = 0.942 2 (0.850+0.857+0.846)/3 = 0.851 x (4.000/4.004) = 0.850 3 (1.074+1.079+1.087)/3 = 1.080 x (4.000/4.004) = 1.079 4 (1.109+1.143+1.139)/3 = 1.130 x (4.000/4.004) = 1.129
4.004 4.000
Classical Decomposition Illustration: Step 2
• Compute the
deseasonalized sales by dividing original sales by the adjusted seasonal index
Ex (Yr 1, Qtr 1):
(55 / 0.942)
= 58.386
Table 4: Deseasonalizing Sales
Adjusted
Original Seasonal Deseasonalized Year Quarter Period Sales Index Sales
t Y S TCe
1 1 1 55 0.942 58.386
2 2 47 0.850 55.294
3 3 65 1.079 60.241
4 4 70 1.129 62.002
2 1 5 65 0.942 69.002
2 6 58 0.850 68.235
3 7 75 1.079 69.509
4 8 80 1.129 70.859
3 1 9 65 0.942 69.002
2 10 62 0.850 72.941
3 11 80 1.079 74.143
4 12 85 1.129 75.288
4 1 13 70 0.942 74.310
2 14 65 0.850 76.471
3 15 85 1.079 78.777
4 16 90 1.129 79.717
Classical Decomposition Illustration: Step 3
• Compute the trend-cyclical regression equation using simple linear regression T
t= a + bt
t-bar = 8.5 T-bar = 69.6
b = 1.465
a = 57.180 T
t= 57.180 + 1.465t
Table 5: Regression Equation Values
Deseasonalized Year Quarter Period Sales
t TCe = (Y/S) t(Y/S) t2
1 1 1 58.386 58.386 1
2 2 55.294 110.588 4
3 3 60.241 180.723 9
4 4 62.002 248.007 16
2 1 5 69.002 345.011 25
2 6 68.235 409.412 36
3 7 69.509 486.562 49
4 8 70.859 566.873 64
3 1 9 69.002 621.019 81
2 10 72.941 729.412 100
3 11 74.143 815.570 121
4 12 75.288 903.454 144
4 1 13 74.310 966.030 169
2 14 76.471 1070.588 196
3 15 78.777 1181.650 225
4 16 79.717 1275.465 256
136 1114.176 9968.750 1496
Classical Decomposition Illustration: Step 4
• (a) Develop trend sales T
t= 57.180 + 1.465t Ex (Yr 1, Qtr 1):
T
1= 57.180 + 1.465(1)
= 58.645
Table 6: Trend Sales
Original Deseasonalized Trend Year Quarter Period Sales Sales Sales
t Y TCe = (Y/S) T
1 1 1 55 58.386 58.645
2 2 47 55.294 60.110
3 3 65 60.241 61.575
4 4 70 62.002 63.040
2 1 5 65 69.002 64.505
2 6 58 68.235 65.970
3 7 75 69.509 67.435
4 8 80 70.859 68.900
3 1 9 65 69.002 70.365
2 10 62 72.941 71.830
3 11 80 74.143 73.295
4 12 85 75.288 74.760
4 1 13 70 74.310 76.225
2 14 65 76.471 77.690
3 15 85 78.777 79.155
4 16 90 79.717 80.620
5 1 17 82.085
2 18 83.550
3 19 85.015
4 20 86.480
Classical Decomposition Illustration: Step 4
• (b) Forecast sales for each of the four quarters of the coming year
Ex (Yr 5, Qtr 1):
0.942 x 82.085
= 77.324
Table 7: Forecasted Sales
Seasonal Trend Forecasted Year Quarter Period Index Sales Sales
t S T TS
1 1 1 0.942 58.645
2 2 0.850 60.110
3 3 1.079 61.575
4 4 1.129 63.040
2 1 5 0.942 64.505
2 6 0.850 65.970
3 7 1.079 67.435
4 8 1.129 68.900
3 1 9 0.942 70.365
2 10 0.850 71.830
3 11 1.079 73.295
4 12 1.129 74.760
4 1 13 0.942 76.225
2 14 0.850 77.690
3 15 1.079 79.155
4 16 1.129 80.620
5 1 17 0.942 82.085 77.324
2 18 0.850 83.550 71.018
3 19 1.079 85.015 91.731
4 20 1.129 86.480 97.636
Classical Decomposition Illustration: Graphical Look
Graph 1: Comparison of Trend, Original, and Deseasonalized Sales
40 50 60 70 80 90 100
0 2 4 6 8 10 12 14 16 18
Quarter Sales ($) (Y/S) = TCe
Deseasonalized
Y Original T
Trend
• Smooth the time series to remove
random effects and seasonality. • Calculate moving averages.
• Determine “period factors” to isolate the (seasonal)
•(error)
factor. • Calculate the ratio y
t/MA
t.
• Determine the “unadjusted
seasonal factors” to eliminate the random component from the period factors
The Classical Decomposition- Procedure
• Average all the y
t/MA
tthat
correspond to the same season.
• Determine the “adjusted seasonal factors”.
Calculate:
[Unadjusted seasonal factor]
[Average seasonal factor]
• Determine “Deseasonalized data
values”. Calculate:
y
t[Adjusted seasonal factors]
t• Determine a deseasonalized trend forecast.
The Classical Decomposition- Procedure – Contd.
Use linear regression on the deseasonalized time series.
Calculate:
(y
t/Ma
t)
•[Adjusted seasonal forecast].
• Determine an “adjusted seasonal
forecast”.
Monitoring and Controlling Operations Forecasts
• Reasons for out-of-control forecasts
– change in trend
– appearance of cycle – politics
– weather changes
– promotions
Monitoring and Controlling a Forecasting Model
Forecasts can be monitored using either Tracking Signal (TS) or Control Charts
• Why track the forecast?
– To plan around the error in the future
– To measure actual demand versus forecasts
– To improve our forecasting methods
Monitoring and Controlling a Forecasting Model
• Tracking Signal (TS)
– The TS measures the cumulative forecast error over n periods in terms of MAD
– If the forecasting model is performing well, the TS should be around zero
– TS indicates the direction of the forecasting error
• if the TS is positive -- increase the forecasts,
• if the TS is negative -- decrease the forecasts.
n
i i
1
(Actual demand - Forecast demand ) TS =
MAD
∑
i=Monitoring and Controlling a Forecasting Model
• Tracking Signal
– The value of the TS can be used to automatically trigger new parameter values of a model, thereby correcting model performance.
– If the limits are set too narrow, the parameter values will be changed too often.
– If the limits are set too wide, the parameter values will
not be changed often enough and accuracy will suffer.
Mo Fcst Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10
Error = Actual - Forecast
= 90 - 100 = -10
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10
RSFE = 6 Errors
= NA + (-10) = -10
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10
Abs Error = |Error|
= |-10| = 10
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10
Cum |Error| = 6 |Errors|
= NA + 10 = 10
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum
|Error| MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0
MAD = 6 |Errors|/n
= 10/1 = 10
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1
TS = RSFE/MAD
= -10/10 = -1
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1 -5
Error = Actual - Forecast
= 95 - 100 = -5
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1 -5 -15
RSFE = 6 Errors
= (-10) + (-5) = -15
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1 -5 -15 5
Abs Error = |Error|
= |-5| = 5
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1
-5 -15 5 15
Cum Error = 6 |Errors|
= 10 + 5 = 15
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1 -5 -15 5 15 7.5
MAD = 6 |Errors|/n
= 15/2 = 7.5
|Error|
Tracking Signal Computation
Mo Forc Act Error RSFE Abs
Error Cum MAD TS
1 100 90 2 100 95 3 100 115 4 100 100 5 100 125 6 100 140
-10 -10 10 10 10.0 -1 -5 -15 5 15 7.5 -2
|Error|
TS = RSFE/MAD
= -15/7.5 = -2
Tracking Signal Computation
Plot of a Tracking Signal
Time Lower control limit Upper control limit
Signal exceeded limit
Tracking signal
Acceptable range
M AD
+
0
-
Tracking Signals
0 20 40 60 80 100 120 140 160
0 1 2 3 4 5 6 7
Time
Actual Demand
-3 -2 -1 0 1 2 3
Tracking Singal
Tracking Signal Forecast
Actual demand
¾ The cumulative forecast error reflects the bias in forecasts, which is the persistent tendency for forecasts to be greater or less than the actual values of a time series.
¾ Tracking signal values are compared to predetermined limits
based on judgment and experience. They often range from r3 to r8; for the most part, we shall use limits of ±4, which are roughly comparable to three standard deviation limits.
¾ Values within the limits suggest –but do not guarantee–that the forecast is performing adequately.
NOTE on TS
Statistical Control Charts
V = ¦(D
t- F
t)
2n - 1
9 This methods assumes (a) Forecast errors are randomly distributed around a mean of zero and (b) The
distribution of errors is normal.
The control chart approach involves setting upper and lower limits for individual forecast errors (instead of cumulative errors, as in the case with a tracking signal). The limits are multiples of the “square root of MSE”
(The square root of MSE is used in practice as an estimate of the standard deviation, V , of the distribution of errors).
9 Using V we can calculate statistical control limits for the
forecast error
Statistical Control Charts (Contd.)
9 Recall that for a ND, approximately 95% of the values (errors in this case) can be expected to fall within limits of 0 r 2V, and approximately 99.7% of the values can be expected to fall within r 3V of zero.
9 Hence, if the forecast is “in control”, 99.7% or 95% of the errors should fall within the limits, depending upon whether r 3V or r 2V limits are used.
9 Points that fall outside these limits should be regarded as
evidence that corrective action is needed [that is the forecast is
not performing adequately).
Statistical Control Charts
Errors
18.39 – 12.24 – 6.12 – 0 – -6.12 – -12.24 – -18.39 –
| | | | | | | | | | | | |
0 1 2 3 4 5 6 7 8 9 10 11 12
Period
Statistical Control Charts
Errors
18.39 – 12.24 – 6.12 – 0 – -6.12 – -12.24 – -18.39 –
| | | | | | | | | | | | |
0 1 2 3 4 5 6 7 8 9 10 11 12
Period UCL = +3V
LCL = -3V
Ranging Forecasts
• Forecasts for future periods are only estimates and are subject to error.
– One way to deal with uncertainty is to develop best-estimate forecasts and the ranges within which the actual data are likely to fall.
• The ranges of a forecast are defined by the upper
and lower limits of a confidence interval.
Ranging Forecasts
• The ranges or limits of a forecast are estimated by:
Upper limit = Y + t(s
yx) Lower limit = Y - t(s
yx) where:
Y = best-estimate forecast
t = number of standard deviations from the mean
of the distribution to provide a given probability of exceeding the limits through chance
s
yx= standard error of the forecast
Ranging Forecasts
• The standard error (deviation) of the forecast is computed as:
2 yx
y - a y - b xy s =
n - 2
∑ ∑ ∑
Example: Railroad Products Co.
• Ranging Forecasts
Recall that linear regression analysis
provided a forecast of annual sales for RPC in year 8 equal to $20.55 million.
Set the limits (ranges) of the forecast so
that there is only a 5 percent probability of
exceeding the limits by chance.
Example: Railroad Products Co.
• Ranging Forecasts
Step 1: Compute the standard error of the forecasts, s
yx.
Step 2: Determine the appropriate value for t.
n = 7, so degrees of freedom = n – 2 = 5.
Area in upper tail = .05/2 = .025 Statistical Table shows t = 2.571.
1287.5 .528(93) .0801(15, 440)
.5748
yx