Professional Documents
Culture Documents
Chapter 4 Forecasting Solution Manual
Chapter 4 Forecasting Solution Manual
C H A P T E R
Forecasting
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
DISCUSSION
QUESTIONS
1. Qualitative models
incorporate subjective factors
into the forecasting model.
Qualitative models are useful
where all previous values are
weighted with a set of
weights that decline
exponentially.
8. MAD, MSE, and MAPE
are common measures of
forecast accuracy. To find the
4 assumption that the future is
a function of the past,
whereas an associative model
incorporates into the model
the variables of factors that
might influence the quantity
being forecast.
18. Independent variable
(x) is said to explain
variations in the dependent
variable (y).
19. Nearly every industry
has seasonality. The
seasonality must be filtered
when subjective factors are
more accurate forecasting 11. A time series is a out for good mediumrange
important. When quantitative
model, forecast with each sequence of evenly spaced data planning (of production and
data are difficult to obtain,
tool for several periods where points with the inventory) and performance
qualitative models may be
the demand outcome is four components of trend, evaluation.
appropriate.
known, and calculate MSE, seasonality, cyclical, and 20. There are many
2. Approaches are MAPE, or MAD for each. random variation. examples. Demand for raw
qualitative and quantitative. The smaller error indicates 12. When the smoothing materials and component
Qualitative is relatively the better forecast. constant, , is large (close to parts such as steel or tires is a
subjective; quantitative uses
9. The Delphi technique 1.0), more weight is given to function of demand for goods
numeric models.
involves: recent data; when is low such as automobiles.
3. Shortrange (under 3 (close to 0.0), more weight is 21. Obviously, as we go
(a) Assembling a group
months), mediumrange (3 given to past data. farther into the future, it
of experts in such a
months to becomes more difficult to
manner as to preclude 13. Seasonal patterns are of
3 years), and longrange (over make forecasts, and we must
direct communication fixed duration and repeat
3 years). diminish our reliance on the
between identifiable regularly. Cycles vary in
4. The steps that should be members of the group length and regularity. forecasts.
used to develop a Seasonal indices allow
(b) Assembling the
forecasting
responses of each “generic” forecasts to be ETHICAL DILEMMA
system are: made specific to the month, This exercise, derived from
expert to the
(a) Determine the questions or week, etc., of the application. an actual situation, deals as
purpose and use of the problems of interest 14. Exponential smoothing much with ethics as with
forecast weighs all previous values forecasting. Here are a few
(c) Summarizing these points to consider:
(b) Select the item or responses with a set of weights that
quantities that are to be decline exponentially. It can No one likes a system
(d) Providing each they don’t understand,
forecasted place a full weight on the
expert with the summary of and most
(c) Determine the time most recent period (with an
all responses college presidents
horizon of the forecast alpha of 1.0). This, in effect,
(e) Asking each expert is the naïve approach, which would feel
(d) Select the type of to study the summary places all its emphasis on last uncomfortable with
forecasting model to be used of the responses period’s actual demand. this one. It does offer
(e) Gather the necessary and respond again to the advantage of
15. Adaptive forecasting
data the questions or depoliticizing the
refers to computer
(f) Validate the problems of interest. funds al
monitoring of tracking
forecasting model (f) Repeating steps (b) signals and selfadjustment if location if used wisely
through (e) several a signal passes its present and fairly. But to do
(g) Make the forecast
times as necessary to limit. so means all parties
(h) Implement and obtain convergence must have input to the
evaluate the results 16. Tracking signals alert process (such as
in responses. If
the user of a forecasting tool smoothing constants)
5. Any three of: sales convergence has not
to periods in which the and all data need to be
planning, production been obtained by the
forecast was in significant open to everyone.
planning and budgeting, cash end of the fourth
error.
budgeting, analyzing various cycle, the responses The smoothing
operating plans. at that time should 17. The correlation constants could be
probably be accepted coefficient measures the selected by an agreed
6. There is no mechanism
and the process degree to which the upon criteria (such as
for growth in these models;
terminated—little independent and dependent lowest MAD) or could
they are built exclusively
additional variables move together. A be based on input
from historical demand
convergence is likely negative value would mean from experts on the
values. Such methods will
if the process is that as X increases, Y tends board as well as the
always lag trends.
continued. to fall. The variables move college.
7. Exponential smoothing is together, but move in
a weighted moving average 10. A time series model Abuse of the system
opposite directions.
predicts on the basis of the is tied to assigning
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall. 28
CHAPTER 4 F O R E C A S T I N G 29
alphas based on what 2. What happens to the 4. At what level of alpha is No, they are not the
results they yield, graph when alpha equals the mean absolute deviation same values. For example,
rather than what one? (MAD) minimized? an intercept of 57.81 with a
alphas make the most The forecast follows the alpha = .16 slope of 9.44 yields a MAD
sense. same pattern as the demand of 7.17.
4.2 (a) No, the data appear to have no consistent pattern
(see part d for graph).
Year 1 2 3 4 5 6 7 8 9 10 11 Forecas
t
Demand 7 9 5 9.0 13.0 8.0 12.0 13.0 9.0 11.0 7.0
(b) 3-year moving 7.0 7.7 9.0 10.0 11.0 11.0 11.3 11.0 9.0
(c) 3-year weighted 6.4 7.8 11.0 9.6 10.9 12.2 10.5 10.6 8.4
Regression is open to (except for the first ACTIVE MODEL 4.3: END-OF-CHAPTER
abuse as well. Models forecast) but is offset by one Exponential Smoothing
can use many years of period. This is a naïve with
PROBLEMS
data yielding one forecast. Trend Adjustment 374 + 368 + 381
4.1 (a) 374.33 pints
result or few years 3. Generalize what happens 1. Scroll through different 3
yielding a to a forecast as alpha values for alpha and beta. (b)
totally different increases. Which smoothing constant
forecast. Selection of Weight
As alpha increases the appears to have the greater Week Pint ed
associative variables forecast is more sensitive to effect on the graph? of s Moving
can have a major changes in demand. alpha Use Averag
impact on results as
*Active Models 4.1, 4.2, 4.3, d e
well.
and 4.4 appear on our Web August 360Error
Forecasti
site, Week of Pints Forecast 31ng .20 Foreca
Active Model www.pearsonhighered.com/h Septe
Error 389 st 381
Exercises* eizer. August 31 360 360 mber
0 7 0 360 .1
September 7 389 360 29 5.8 =
365.8
ACTIVE MODEL 4.1: September 14 410 365.8 44.2 8.84 38.1
374.64
Moving Averages September 21 381 374.64 Septe
6.36 4101.272 375.91368
mber 2 .3
1. What does the graph 14 =
September 28 368 375.912 –7.912 –1.5824 374.32
look like when n = 1?
96 110.
The forecast graph October 5 374 374.3296–.3296 –.06592 374.264
mirrors the data graph but Septe 381 36 374
one period later. mber .6
2. With beta set to zero, 21 =
2. What happens to the find the best alpha and 224.
graph as the number of observe the MAD. Now find 4
periods in the moving the best beta. Observe the Septe 368
average increases? MAD. Does the addition of a mber
The forecast graph trend improve the forecast? 28
becomes shorter and alpha = .11, MAD = Octobe 374
smoother. r5
2.59; beta above .6 changes
Forec
3. What value for n the MAD (by a little) to
ast
minimizes the MAD for this 2.54.
372.9
data?
ACTIVE MODEL 4.4: (c)
n = 1 (a naïve forecast)
Trend Projections The forecast is 374.26.
ACTIVE MODEL 4.2: 1. What is the annual trend
Exponential Smoothing in the data?
1. What happens to the 10.54
graph when alpha equals 2. Use the scrollbars for the
zero? slope and intercept to
The graph is a straight determine the values that
line. The forecast is the minimize the MAD. Are
same in each period. these the same values that
regression yields?
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
30 CHAPTER 4 F O R E C A S T I N G
Two-Year � 420 �
Year Mileage Moving Average MAD 140 �
� 3 � �
(0.1 20)
1 3,000 + (0.2
4.5 (d)
2 4,000 20)
3 3,400 3,500 Forecast
4 3,800 3,700 Year Mileage Forecast Error
+
5 3,700 3,600 1 3,000 3,000
(0.2
2 4,000 3,000 1,000
3 3,400 3,500
4 3,800 3,450 21)
300 5 3,700 3,625 +
MAD 100. Total (0.3
3
23)]/
The forecast is 3,663 miles.
1.0
4.6
= 20.6
Y Sales X Period
[iv] Exponential
January 20 smoothing with
February 21
alpha = 0.3
March 15
April 14 FOct 18 + 0.3(20 - 18) 18.6
May 13 FNov 18.6 + 0.3(20 - 18.6) 19.0
Naïve tracks the ups June 16
July 17 FDec 19.02 + 0.3(21 - 19.02) 1
and downs best but lags
August 18 FJan 19.6 + 0.3(23 - 19.6) 20.6
the data by one period.
September 20
Exponential smoothing October 20 10 [v] Trend
is probably better November 21 11 � x 78, x 6.5, � y = 218, y 18.
because it smoothes the December 23 12
data and does not have � xy - nx y
Sum 218 78 b
as much variation. � x 2 - nx 2
Average 18.2
TEACHING NOTE: 1474 - (12)(6.5)(18.2) 54.4
b 0.38
Notice how well 650 - 12(6.5)2 143
(a)
exponential smoothing a y - bx
forecasts the naïve. a 18.2 - 0.38(6.5) 15.73
4.4 (a) FJuly FJune + 0.2(Forecasting error) Forecast = 15.73
42 + 0.2(40 �42) 41.6 + .38(1
3) =
(b) FAugust FJuly + 0.2(Forecasting error) 20.67,
41.6 + 0.2(45 - 41.6) 42.3 where
next
January
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 31
4.9 (d) Table for Problem 4.9(d):
= .1 = .3 = .5
Table for Problem 4.9 (a, b, c)
Month Price per Forecast |Error| Forecast |Error| Forecast |Error|
Chip Forecast |Error|
January $1.80 $1.80 $.00
Two-Month$1.80 $.00
Three- $1.80 $.00
Two-Month Three-
February 1.67 1.80 .13 1.80 .13
Month 1.80 .13 Month
March 1.70 Price per
1.79 .09Moving 1.76 Moving
.06 1.74 Moving.04 Moving
April Month 1.85 Chip
1.78 Average
.07 1.74 Average
.11 1.72 Average
.13 Average
May January
1.90 $1.80
1.79 .11 1.77 .13 1.78 .12
June February
1.87 1.67
1.80 .07 1.81 .06 1.84 .03
July March1.80 1.70
1.80 .00 1.735 1.83 .03 1.86 .035.06
August April 1.83 1.85
1.80 .03 1.685 1.82 1.723
.01 1.83 .165.00 .127
May 1.90 1.775 1.740 .125 .160
Septembe 1.70 1.81 .11 1.82 .12 1.83 .13
June 1.87 1.875 1.817 .005 .053
r
July 1.80 1.885 1.873 .085 .073
October 1.65 1.80 .15 1.79 .14 1.76 .11
August 1.83 1.835 1.857 .005 .027
November 1.70 1.78 .08 1.75 .05 1.71 .01
September 1.70 1.815 1.833 .115 .133
December 1.75
October 1.77
1.65 .02 1.765 1.73 .02
1.777 1.70 .115.05 .127
Totals
November 1.70 $.8 1.675 $.8
1.727 $.81
.025 .027
December 1.75 6 1.675 6
1.683 .075 .067
MAD (total/12) $.072 $.072
Totals . $.067 .793
5
= .5 is preferable, using MAD, to = .1 or = .3. One could
4.10 Year 1 2 3 4 5 6 7 8 9 10 11 Forecast
Demand 4 6 4 5.0 10.0 8.0 7.0 9.0 12.0 14.0 15.0
(a) 3-year moving 4.7 5.0 6.3 7.7 8.3 8.0 9.3 11.7 13.7
(b) 3-year 4.5 5.0 7.3 7.8 8.0 8.3 10.0 12.3 14.0
weighted
forecast becomes 56.3, or (96 + 88 + 90)
56 patients. 4.8 (a) 91.3
is the 3 results appear in
13th the figure below.
month.
(c) Only trend provides
an equation
that can
extend
beyond one
month
4.7 Present = Period (week)
6.
��1 � �1 � �1 � �1 � �
a) So: F7 ��3 �A6 + � 4 �A5 + �4 �A4 + �6 �A3 � 1.0
�� � � � � � � � �
�1 � �1 � �1 � �1 �
� �(52) + � �(63) + � �(48) + � �(70) = 56.76 patients,
3
� � 4
� � 4
� � �6 � or 57 patients
where
(c) MAD (twomonth
1 1 1 1 moving average) = .750/10
1.0 = � weights , , ,
3 4 4 6 MAD = 13.5/5 = 2.7
= .075
b) If the weights are 20, 15, (d) MSE = 66.75/5 = MAD (threemonth
15, and 10, there will be 13.35 moving average) = .793/9 = .
no change in the forecast (e) MAPE = 14.94%/5 088
because these are the = 2.99% Therefore, the twomonth
same relative weights as 4.9 (a, b) The computations moving average seems to
in part (a), i.e., 20/60, for both the two have performed better.
15/60, 15/60, and 10/60. and threemonth
c) If the weights are 0.4, 0.3, averages appear
0.2, and 0.1, then the in the table; the
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
32 CHAPTER 4 F O R E C A S T I N G
(b) |Error| = |Actual – Forecast|
4.11 (a) Year 1 2 3 4 5 6 7 8 9 10 11 Forecast
Year 1 2 3 4 5 6 7 8 9 10 11 MAD
Demand 4 6.0 4.0 5.0 10.0 8.0 7.0 9.0 12.0 14.0 15.0
Exp. smoothing
Exp. Smoothing 5 4.7 5.1 14.8 1.3 4.8 1.1
6.4 0.2 6.9 5.2 6.9 1.6 7.5 0.1 8.9 2.1 10.4 4.5 11.85.1 4.6 2.4
These calculations were completed in Excel. Calculations are slightly different in Excel OM and POM for Windows due to
rounding differences.
4.12 2 50
3 52
Actual 4 56 (45 + 50 + 52)/3 = 4
t Day Demand 5 58 (50 + 52 + 56)/3 =
1 Monday 88 52.7
6 ? (52 + 56 + 58)/3 =
2 Tuesday 72 55.3
3 Wednesday 68
= 12.3
4 Thursday 48 MAD = 6.2
5 Friday (c) Trend projection:
Ft = Ft–1 + (At–1 – Ft–1)
Let = .25. Let Monday Year Demand Trend Projection
forecast demand = 88 1 45 42.6 + 3.2 1 = 45.8
(c) The forecasts are
F2 = 88 + .25(88 – 88) = 88 2 50 42.6 + 3.2 2 = 49.0
about the same. 3 52 42.6 + 3.2 3 = 52.2
+ 0 = 88
4 56 42.6 + 3.2 4 = 55.4
F3 = 88 + .25(72 – 88) = 88
5 58 42.6 + 3.2 5 = 58.6
– 4 = 84 6 ? 42.6 + 3.2 6 = 61.8
F4 = 84 + .25(68 – 84) = 84
= 3.2
– 4 = 80
MAD = 0.64
F5 = 80 + .25(48 – 80) = 80 Y a + bX
– 8 = 72
�XY �nXY
4.13 (a) Exponential b
�X 2 �nX 2
smoothing, = 0.6:
a Y �bX
Exponential
Year Demand Smoothing X Y XY X2
1 45 41
2 50 1
41.0 + 0.6(45–41) = 45
43.4 45 1
3 52 2
43.4 + 0.6(50–43.4) 5047.4
= 100 4
4 56 3
47.4 + 0.6(52–47.4) 5250.2
= 156 9
5 58 4
50.2 + 0.6(56–50.2) 5653.7
= 224 16
6 ? 5
53.7 + 0.6(58–53.7) 5856.3
= 290 25
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 33
4.17 or –2 = –8
So, .25 =
Forecast Exponential
Year Sales Smoothing Now we can find F5 : F5 =
50 + (46 – 50)
2005 450 410.0
2006 495 410 + 0.6(450 – 410) = 434.0 F5 = 50 + 46 – 50
2007 518 434 + 0.6(495 – 434) = 470.6 = 50 – 4
2008 563 470.6 + 0.6(518 – 470.6) = For = .25, F5 = 50 –
499.0 4(.25) = 49
2009 584 499 + 0.6(563 – 499) = 537.4
2010 537.4 + 0.6(584 – 537.4) = The forecast for time period 5
565.6 = 49 units.
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
34 CHAPTER 4 F O R E C A S T I N G
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 35
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
36 CHAPTER 4 F O R E C A S T I N G
Quarte 2007 2008 2009 4.29 2011 is 25 years Then y = a + bx, where y =
r beyond 1986. Therefore, the number sold, x = price, and
2011 quarter numbers are 101
Winter 73 65 89
through 104.
Spring 104 82 146
Summer 168 124 205 (2) (3)
Fall 74 52 98 (1) Quarter Forecast
Quarter Number (77 + .
43Q
Winter 101 120.43
Spring 102 120.86
Summer 103 121.29
Fall 104 121.72
4.30 Given Y = 36 + 4.3X
(a) Y = 36 +
4.3(70) = 337
(b) Y = 36 +
4.3(80) = 380
(c) Y = 36 +
4.3(90) = 423
4.31 Let x1, x2 , K , x6 be the prices and y1, y2 , K , y6
be the number sold.
4.33 (a) See the table below.
6
�xi
X i 12,880 Average price = 3.2583
- 5(3)(180) 2,880 - 2,700 (1)
b6
6 55 - 5(3)2 55 - 45
yi
�180
Y i1 Average number sold = 550
18 (2)
610
6 a 180 - 3(18) 180 - 54 126
�xi yi 9,783 (3)
i 1 y 126 + 18 x
6
2
�xi = 67.1925 (4)
i1
6
�xi yi - nx y
i 1 (9, 783) - 6(3.25833)(550)
b 6
2
�x i - nx
2 67.1925 - 6 (3.25833)2
i 1
-969.489
-277.6
3.49222
a y - bx 550 - [(-277.6)(3.25)] 1, 454.6
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
4.32 (a) x y xy x2
16 330 5,280 256
12 270 3,240 144
18 380 6,840 324
14
CHAPTER 4 F300
O R E C A S4,200
TING 196 37
60 1,280 19,560 920
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
38 CHAPTER 4 F O R E C A S T I N G
5 81.1 40
(b) Developing the
6 89.0 55 regression
relationship, we have:
7 101.1 60 (Summe Tourists Ridership
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 39
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
40 CHAPTER 4 F O R E C A S T I N G
standard error
of the estimate and
the MAD, the 0.2
constant is
better. However,
other smoothing
constants need to
be examined.
Actual Smoothed
t A(t) Ft ( =
0.2)
1 50 +50.0
2 35 +50.0
3 25 +47.0
4 40 +42.6
5 45 +42.1
6 35 +42.7
7 20 +41.1
8 30 +36.9
9 35 +35.5
10 20 +35.4
11 15 +32.3
12 40 +28.9
13 55 +31.1
14 35 +35.9
15 25 +36.7
16 55 +33.6
17 55 +37.8
18 40 +41.3
19 35 +41.0
20 60 +39.8
21 75 +43.9
22 50 +50.1
23 40 +50.1
24 65 +48.1
25 +51.4
MAD
(c) Students should
note how stable
the smoothed
values are for =
0.2. When
compared to actual
week 25 calls of
85, the smoothing
constant, = 0.6,
appears to do a
slightly better job.
On the basis of the
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 41
4.44 XY - nXY
b
Week Actual Value Smoothed 87Trend Estimate Forecast Forecas X 2 - nX 2
So: MAD:
Value
10.875 t
8 a Y - bX
t At Ft ( = 0.3)
39 Tt ( = 0.2) FITt Error
3.586
1 50.000 50.00010.875 0.000 50.000 0.000
2 35.000 50.000 0.000 50.000 –15.000
3 25.000 45.500 –0.900 44.600 –19.600
4 40.000 38.720 –2.076 36.644 3.356
5 45.000 37.651 –1.875 35.776 9.224
6 35.000 38.543 –1.321 37.222 –2.222
7 20.000 36.555 –1.455 35.101 –15.101
8 30.000 30.571 –2.361 28.210 1.790
9 35.000 28.747 –2.253 26.494 8.506
10 20.000 29.046 –1.743 27.303 –7.303
11 15.000 25.112 –2.181 22.931 –7.931
12 40.000 20.552 –2.657 17.895 22.105
13 55.000 24.526 –1.331 23.196 31.804
14 35.000 32.737 0.578 33.315 1.685
15 25.000 33.820 0.679 34.499 –9.499
16 55.000 31.649 0.109 31.758 23.242
17 55.000 38.731 1.503 40.234 14.766
18 40.000 44.664 2.389 47.053 –7.053
19 35.000 44.937 1.966 46.903 –11.903
20 60.000 43.332 1.252 44.584 15.416
21 75.000 49.209 2.177 51.386 23.614
22 50.000 58.470 3.594 62.064 –12.064
23 40.000 58.445 2.870 61.315 –21.315
24 65.000 54.920 1.591 56.511 8.489
25 59.058 2.100 61.158
4.46 (a) X Y
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
42 CHAPTER 4 F O R E C A S T I N G
and X = 6885, Y = 36.96, (b, c) Amit wants to 4.48 (a) 27 7.70 5.497 2.20
XY = 20299.5, X 2 = forecast by 28 10.10 6.818 3.28
Quarter Contracts Sales Y 29 15.20 8.787 6.41
3857893, exponential X
Y 2 = 110.26, X = 529.6, smoothing (setting (Continued)
1 153 8
Y = 2.843, Then: February’s forecast
2 172 10
equal to January’s
20299.5 - 13 529.6 2.843 20299.5 - 19573.5 3 197 15
b sales) with alpha
4 178 9
3857893 - 13 529.62 3857893 - 3646190
0.1. Barbara wants
5 185 12
726 to use a 3period
0.0034 6 199 13
211703 moving average.
7 205 12
a 2.84 - 0.0034 529.6 1.03 Sales Amit 8
Barba 226 16
and Y = 1.03 + 0.0034X Totals 1,51 95
January 400 — 5
As an indication of the
February 380 400 Average 189.375
usefulness of this 11.875
March 410 398
relationship, we can calculate
April 375 399.2 396.67
b = (18384 – 8 189.375
the correlation coefficient: May 405 396.8 388.33
11.875)/(290,413 – 8
MAD
n XY - X Y 189.375
r
n X 2 - ( X ) n Y 2 - ((d)
2 2 189.375) = 0.1121
Y )
Note that Amit has more
a = 11.875 – 0.1121
forecast observations,
189.375 = –9.3495
13 20299.5 - 6885 36.96 while Barbara’s moving
average does not start
Sales ( y) = –9.349 + 0.1121
13 3857893 - 68852 13 110.26 - 36.962 (Contracts)
until month 4. Also note
that the MAD for Amit (b)
263893.5 - 254469.6
is an average of 4 r (8 � 18384 - 1515 � 95) ((8 � 290,413 - 15152 )(8 � 1183 - 952 ))
50152609 - 47403225 1433.4 - 1366.0
numbers, while
9423.9 Barbara’s is only 2. 0.8963
2749384 67.0 Amit’s MAD for Sxy 1183 - (-9.3495 � 95) - (0.112 � 18384 / 6) 1.3408
9423.9 exponential smoothing
0.692 r 2 .8034
1658.13 8.21 (16.11) is lower than
that of Barbara’s 4.49 (a)
r 2 0.479 moving average (19.17). Method Exponential Smoothing
A correlation coefficient of So his forecast seems to 0.6 =
0.692 is not particularly high. be better. Year Deposits Forecast
The coefficient of (Y )
2
determination, r , indicates 1 0.25 0.25
that the model explains only 2 0.24 0.25
47.9% of the overall 3 0.24 0.244
variation. Therefore, while 4 0.26 0.241
the model does provide an 5 0.25 0.252
estimate of GPA, there is 6 0.30 0.251
7 0.31 0.280
considerable variation in
8 0.32 0.298
GPA, which is as yet 9 0.24 0.311
unexplained. For 10 0.26 0.268
11 0.25 0.263
(b) X 350: Y 1.03 + 0.0034 � 350 2.22 12 0.33 0.255
(c) X 800: Y 1.03 + 0.0034 � 800 3.75 13 0.50 0.300
14 0.95 0.420
Note: When solving this 15 1.70 0.738
problem, care must be taken to 16 2.30 1.315
interpret significant digits. Also 17 2.80 1.906
note that X = 800 is outside the 18 2.80 2.442
range of the data set used to 19 2.70 2.656
determine the regression 20 3.90 2.682
relationship, so caution is 21 4.90 3.413
advised. 22 5.30 4.305
23 6.20 4.90
4.47 (a) There is not a 24 4.10 5.680
strong linear trend in sales 25 4.50 4.732
over time. 26 6.10 4.592
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 43
4.49 (a) (Continued) appropriate
choice. Measures
Method Exponential Smoothing
0.6 = of error and
Year Deposits Forecast goodnessoffit are
(Y ) really irrelevant.
30 18.10 12.6350 Exponential
31 24.10 15.9140 smoothing
32 25.60 20.8256 provides a forecast
33 30.30 23.69 only of deposits
34 36.00 27.6561 for the next year—
35 31.10 32.6624 and thus does not
36 31.70 31.72
Forecasting Summary Table
37 38.50 31.71 Exponential Linear Regression
38 47.90 35.784 Method used: Smoothing (Trend Analysis) Linear Regression
39 49.10 43.0536 Y = –18.968 + Y = –17.636 +
40 55.80 46.6814 1.638 YEAR 13.59364
41 70.10 52.1526 GSP
42 70.90 62.9210 MAD 3.416 10.587 10.255
43 79.10 67.7084 MSE 34.39 171.817 204.919
44 94.00 74.5434 Standard error using 6.075 13.416 14.651
TOTALS 787.30 n – 2 in denominator
Correlation coefficient 0.846 0.813
AVERAGE 17.8932 31 31 24.10 13 1.20 0.50 –1
32 32 25.60 14 1.20 0.95 –1 address the five
Next period forecast = 86.2173 15 1.20 1.70 –1
33 33 30.30 year forecast
34 34 36.00 16 1.60 2.30 4 problem. In order
17 1.50 2.80 2
35 35 31.10 to use the
Method Linear Regression 36 (Trend36
Analysis) 31.70
18 1.60 2.80 4
regression model
Year Period (X ) Deposits 37 37 38.50 19 1.70 2.70 5 based upon GSP,
1 1 0.25 38 38 47.90
20 1.90 3.90 8 one must first
2 2 0.24 39 39 49.1021 1.90 4.90 8 develop a model
3 3 0.24 40 40 55.8022 2.30 5.30 13 to forecast GSP,
4 4 0.26 41 41 70.1023 2.50 6.20 16 and then use the
5 5 0.25 42 42 70.9024 2.80 4.10 20 forecast of GSP in
43 43 79.1025 2.90 4.50 21 the model to
6 6 0.30
44 44 94.0026 3.40 6.10 28 forecast deposits.
7 7 0.31
27 3.80 7.70 34
8 8 0.32 TOTALS 990.0 787.30 This requires the
28 4.10 10.10 38
9 9 0.24 0
29 4.00 15.20 36
development of
10 10 0.26 AVERAGE 22.50 17.893 30 4.00 18.10 36 two models—one
11 11 0.25 31 3.90 24.10 35 of which (the
12 12 0.33 32 3.80 25.60 34 model for GSP)
33 3.80 30.30 34 must be based
13 13 0.50 Method Least squares–Simple
34 Regression
3.70 36.00on 32 solely on time as
14 14 0.95 35 4.10 31.10 38 the independent
a b 36 4.10 31.70 38
15 15 1.70 variable (time is
–17.636 13.5936 37 4.00 38.50 36
16 16 2.30 the only other
Coefficients GSP Deposit 38 4.50 47.90 43
17 17 2.80 : s variable we are
39 4.60 49.10 44
18 18 2.80 Year (X) (Y ) Forecast
40 4.50 55.80 43
given).
19 19 2.70 (b) One could make a
1 0.40 0.25 –12 41 4.60 70.10 44
20 20 3.90 2 0.40 0.24 –12 42 4.60 70.90 44 case for exclusion
21 21 4.90 3 0.50 0.24 –10 43 4.70 79.10 46 of the older data.
22 22 5.30 4 0.70 0.26 –8 44 5.00 94.00 50 Were we to
23 23 6.20 5 0.90 0.25 –5 TOTALS exclude data from
24 24 4.10 6 1.00 0.30 –4 AVERAGE roughly the first 25
25 25 4.50 7 1.40 0.31 1
years, the forecasts
26 26 6.10 8 1.70 0.32 5
Given that one for the later years
27 27 7.70 9 1.30 0.24
0.036086 wishes to develop would likely be
28 28 10.10 a fiveyear considerably more
10 1.20 0.26 –1
29 29 15.20 forecast, trend accurate. Our
11 1.10 0.25 –2
30 30 18.10 12 0.90 0.33 –5 analysis is the argument would be
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
44 CHAPTER 4 F O R E C A S T I N G
ADDITIONAL
HOMEWORK MAD = 10/4 = 2.5, MSE =
38/4 = 9.5
PROBLEMS
These problems, which appear 4.53 (a) 3month moving
on www.myomlab.com, average:
provide an additional 13
problems that you may wish to Three-Month
assign.
Month Sales Moving Average
4.50
Week 1 2 3 4 5 January
6 7 8 11 9 10 Forecast
February 14
Registration 22 21 25 27 35 March
29 33 3716 41 37
(a) Naïve 22 21 25 27 April
35 29 3310 37 (1141+ 14 37
+ 16)/3 =
(b) 2-week moving 21.5 23 26 31 32 31 35 39 39
(c) 4-week moving 23.7 May
27 29 3115 33.5(14
35+ 16 37
+ 10)/3 =
5
June 17 (16 + 10 + 15)/3 =
=
2
2
.
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 45
(c) Based on a Sales
Month Mean 9.17 Average4.56 To Absolute
Three-Month yMoving compute (b) Correlation
Absolute x 3.5
Moving seasonalized or adjusted sales
Deviation coefficient:
Deviation forecast, we just multiply each n XY - X Y
January 11 y 5.27 + 1.11x
criterion, 14the seasonalized index by the r
February n X 2 - ( X ) 2 n Y 2
3month moving Period 7 forecast = appropriate trend forecast.
March 16
average 10 with 13.07
April (1 11 + 2 14 + 3 16)/6 = 14.50 Y� 4.50 Y�
Index 5 70 - 15 20
MAD = 2.2 is15 to Period
(1 14 + 2 16 12+ forecast
3 10)/6 = = 12.67Seasonal Trend forecast
May 2.33
June be preferred 17
over 18.64, but this is far
(1 16 + 2 10 + 3 15)/6 = 13.50 Hence, for 3.50 5 55 - 152 5 130 - 2
July the 3month 11 outside
(1 10 + 2 15 the
+3 range
17)/6 of = 15.17Quarter I: Y�4.17
I 1.25 120,000 150,000
August weighted moving 14 valid data.
(1 15 + 2 17 + 3 11)/6 = 13.67 0.33 350 - 300
�
Septemberaverage 17 with (1 17 + 2 11 + 3 14)/6 = 13.50 II 0.90 140,000 126,000
Quarter II: Y3.50
October MAD = 2.72. 12 (1 11 + 2 14 + 3 17)/6 = 15.00 3.00
� 275 - 225 650 - 400
Quarter III: Y 0.75 160,000 120,000
III
November 14 (1 14 + 2 17 + 3 12)/6 = 14.00 0.00 50
(d) Other factors 16
that � 0.45
December (1 17 + 2 12 + 3 14)/6 = 13.83 IV 1.10 180,000 198,000
Quarter IV: Y2.17
111.80
January might be included11 (1 12 + 2 14 + 3 16)/6 = 14.67 3.67
February in a more (1 14 + 2 16 + 3
4.57
11)/6 = 13.17
complex model Mon Tue Wed Thu Fri Sat
= 27.17
are interest rates Week 1 210 178 250 215 160 180
and cycle or MAD = 2.72
Week 2 215 180 250 213 165 185
seasonal factors. Week 3 220 176 260 220 175 190
4.54 (a) Week 4 225 178 260 225 176 190
Averages 217. 17 255 218. 16 186.3 Overall average =
Actua Cumulativ 5 8 3 9 204
l
Wee Miles Foreca Error Error (a) Seasonal indices: The correlation coefficient
k st indicates that there is a
1.066 (Mon) 0.873 (Tue)
1 17 17.00 0.00 positive
1.25 (Wed)
2 21 17.00 –4.00 correlation between bank
3 19 17.80 –1.20 1.07 (Thu) 0.828 (Fri)
0.913 (Sat) deposits and consumer price
4 23 18.04 –4.96 –
indices in
5 18 19.03 +1.0 (b) To calculate for
3 Monday of Week
6 16 18.83 +2.8 5 = 201.74 +
3
0.18(25) 1.066 =
7 20 18.26 –1.74
219.9 rounded to
8 18 18.61 +0.6
1 220
9 22 18.49 –3.51 – Forecast 220 (Mon)
10 20 19.19 –0.81 – 180 (Tue) 258 (Wed)
11 15 19.35 +4.3 221 (Thu) 171
5 (Fri) 189 (Sat)
12 22 18.48 –3.52 –
4.58 (a) 4000 +
(b) The MAD = 0.20(15,000) = 7,000
28.56/12 = 2.38
(b) 4000 +
(c) The cumulative 0.20(25,000) = 9,000
error and tracking
signals appear to 4.59 (a) 35 + 20(80) +
be consistently 50(3.0) = 1,785
negative, and at (b) 35 + 20(70) +
week 10, the 50(2.5) = 1,560
tracking signal 4.60 Given: X = 15, Y =
exceeds 5 MADs. 2 2
20, XY = 70, X = 55, Y
Birmingham, Alabama—i.e.,
= 130, X = 3, Y = 4
4.55 y x x2 as one variable tends to
(a) XY - nXY increase (or decrease), the
7 1 1 b
9 2 4 X 2 - nX 2 other tends to increase (or
5 3 9 a Y - bX decrease).
11 4 16
70 - 5 3 4 70 4.60 (c) Standard
- 60 10 error of
10 5 25 b
the estimate: 1
13 6 36 55 - 5 32 55 - 45 10
55 21 91 a 4 - 1 3 4 - 3 1
Y 1 + 1X
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
46 CHAPTER 4 F O R E C A S T I N G
130 - 20 - 70
40
13.3 3.65 Y 2 - a Y - b XY 94 the data.
- 1 20 - 1 70
Syx
3 3 n-2 The 5 - 2importance of
combining a qualitative
4.61 94 - 20 - 70
1.333 1.15 model with a quantitative
X Y 3 model in situations where
2 4 technological change is
1 1 4.62 Using software, the occurring.
4 4
5 6 regression equation is: 1. A plot of the data
3 5 Games lost = 6.41 + 0.533 indicates a linear trend (least
Column Totals 15 20 days rain. squares) model might be
appropriate for forecasting.
Given: Y = a + bX where: Using linear trend you obtain
CASE STUDIES the following:
XY - nXY
b
X 2 - nX 2 1 SOUTHWESTERN x y x2 xy
a Y - bX UNIVERSITY: B 1 480 1 48
This is the second in a series 2 436 4 87
and X = 15, Y = 20, XY = of integrated case studies that 3 482 9 1,44
2 2
70, X = 55, Y = 94, X = run throughout the text. 4 448 16 1,79
3, 5 458 25 2,29
1. One way to address the
Y = 4. Then: 6 489 36 2,93
case is with separate 7 498 49 3,48
70 - 5 4 3 70 - 60 forecasting models for each
b 1.0 8 430 64 3,44
55 - 5 32 55 - 45 game. Clearly, the 9 444 81 3,99
a 4 - 1 3 1.0 homecoming game (week 2) 10 496 100 4,96
and the fourth game (craft 11 487 121 5,35
and Y = 1.0 + 1.0X. The festival) are unique attendance 12 525 144 6,30
correlation coefficient: situations. 13 575 169 7,47
14 527 196 7,37
n XY - X Y 15 540 225 8,10
r Game Model 16 502 256 8,03
n X 2 - ( X ) 2 n Y 2 - ( Y ) 2 17 508 289 8,63
1 y = 30,713 + 2,534x
18 573 324 10,31
2 y = 37,640 + 2,146x
5 70 - 15 20 350 - 300 3 y = 36,940 + 1,560x 19 508 361 9,65
20 498 400 9,96
5 55 - 152 5 94 - 202 275 - 225 470 - 400 4 y = 22,567 + 2,143x
21 485 441 10,18
5 y = 30,440 + 3,146x
Total 22 526 484 11,57
50 50
0.845 23 552 529 12,69
50 70 59.16 24 587 576 14,08
(where y = attendance and x 25 608 625 15,20
= time) 26 597 676 15,52
27 612 729 16,52
2. Revenue in 2010 =
28 603 784 16,88
(239,000) ($50/ticket) = 29 628 841 18,21
$11,950,000 30 605 900 18,15
Revenue in 2011 = 31 627 961 19,43
(250,530) ($52.50/ticket) 32 578 1,024 18,49
= $13,152,825 33 585 1,089 19,30
34 581 1,156 19,75
3. In games 2 and 5, the 35 632 1,225 22,12
forecast for 2011 exceeds 36 656 1,296 23,61
stadium capacity. With this Totals 666 19,366 16,206 378,6
appearing to be a continuing
trend, the time has come for a Average 18.5 537.9 450.2 10,5
new or expanded stadium.
2 DIGITAL CELL
PHONE, INC.
Objectives:
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
CHAPTER 4 F O R E C A S T I N G 47
2
�x - nx 2
16,206 - (36 �18.52 ) ed., Prentice
10th 3885.0 Hall actually protects managers 2004 54.92 38.5
Publishing. from large sales variations 2005 69.70 51.4
a y - bx 537.9 - 5.25 �18.5 440.85 2006 68.90 58.7
Cases = 432.28 + 5.73 outside their control. One
n �xy - �x �y (time), r2 = .93, MAD = could also justify a 50%– 2007 63.72 45.4
r 2008 84.73 50.2
[ n �x 2 - ( �x )2 ][ n �y 2 - ( �y)212.84
] 30%–20% model or some
2009 78.74 79.6
other variation.
(36)(378,661) - c) Additive seasonal model,
(666)(19,366)
4. Other predictors of cafe
2 Cases = 444.29 + 5.06
[(36) �(16,206) - (666) ][(36)(10,558,246) - (19,366)2 ] sales could include season of
(time), r2 = .86, MAD = Southeast Airline D
13,631,796 - 12,897,756
20.02 year (weather); hotel
Airframe Cost Engine
[(583,416) - (443,556)][380,096,856) - (375,041,956)] occupancy; spring break from Year per Aircraft per Airc
d) Additive seasonal model,
colleges; beef prices;
737,040 with
734,040 centered moving 2003 13.29 18.8
promotional budget; etc.
[139,860][5,054,900] averages.
706,978,314,000 2004 25.15 31.5
Cases = 431.31 + 5.72 5. Y a + bx 2005 32.18 40.4
734,040 (time), r2 = .94, MAD = 2006 31.78 22.1
.873 Month Advertising Guest Count
840,820 12.28 X Y
2007 25.34 19.6
2008 32.78 32.5
r 2 .76 The two methods that use 1 14 21 2009 35.56 38.0
y 440.85 + 5.25 (time) the average of all data have 2 17 24
r = 0.873 indicating a
very similar results, and the 3 25 27 Utilizing the software
reasonably good fit two CMA methods also look 4 25 32 package provided with this
quite close. As suggested with 5 35 29 text, we can develop the
The student should this analysis, CMA is typically following regression
report the linear trend results, the better technique. 6 35 37
equations for the variables of
but deflate the forecast interest:
7 45 43
obtained based upon VIDEO CASE Northern Airlines—
qualitative information about
industry and technology
STUDY 8 50 Airframe Maintenance Cost:
43
Cost = 36.10 + 0.0026
trends. FORECASTING AT 9 60 54
Because there is limited Airframe age
HARD ROCK CAFE Coefficient of
seasonality in the data, the 10 60 66
linear trend analysis above There is a short video (8 determination = 0.7695
Totals 36 37
provides a good r2 of .76. minutes) available from Coefficient of
6 6
However, a more precise Prentice Hall and filmed Averag 36.6 37.6 correlation = 0.8772
forecast can be developed specifically for this text that e Northern Airlines—Engine
addressing the seasonality supplements this case. Maintenance Cost:
issue, which is done below. 1. Hard Rock uses Cost = 20.57 + 0.0026
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.
48 CHAPTER 4 F O R E C A S T I N G
Copyright © 2011 Pearson Education, Inc. publishing as Prentice Hall.