Introduction to

Management Science
with Spreadsheets
Stevenson and Ozgur
First Edition

Part 2 Introduction to Management Science and Forecasting

Chapter 2

Forecasting

McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies, Inc. All rights reserved.
 Learning Objectives

After completing this chapter, you should be able to:

1. Explain the importance of forecasting in

organizations.
2. Describe the three major approaches to forecasting.
3. Use a variety of techniques to make forecasts.
4. Measure the accuracy of a forecast over time using
various methods.
5. Determine when a forecast can be improved.
6. Discuss the main considerations in selecting a
forecasting technique.
7. Utilize Excel to solve various forecasting problems.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–2
 The
The Importance
Importance of
of Forecasting
Forecasting
• Forecasting
– is important because it helps reduce uncertainty.
– provides decision makers with an improved picture of
probable future events and, thereby, enable decision
makers to plan accordingly.
– is used for planning the system itself.
– is used for planning the use of the system
– as a process has an inherent tendency for inaccuracy.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–3
 The
The Importance
Importance of
of Forecasting
Forecasting
• The Forecasting Process
1. Determine the purpose of the forecast.
2. Determine the time horizon.
3. Select an appropriate technique.
4. Identify the necessary data, and gather it if
necessary.
5. Make the forecast.
6. Monitor forecast errors in order to determine if the
forecast is performing adequately. If it is not, take
appropriate corrective action.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–4
 Approaches
Approaches to
to Forecasting
Forecasting
• Qualitative Forecasts
– are based on judgment and/or opinion rather than on
the analysis of “hard” data.
• Forecasts That Use Time Series Data
– involve the assumption that past experience reflects
probable future experience (i.e., the past movements
or patterns in the data will persist into the future).
• Explanatory Models
– incorporate one or more variables that are related to
the variable of interest and, therefore, they can be
used to predict future values of that variable.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–5
 Selecting
Selecting the
the Forecasting
Forecasting Technique
Technique
• Factors affecting the choice of the forecasting
technique to be used:
– the importance (purpose) of the forecast
– the desired accuracy of the forecast
– the cost of developing the forecast
– resources available to support and conduct the
forecasting process
– the planning horizon (long- or short-term)
– the sophistication of the users of the forecast
– A good rule is to choose the simplest technique that
gives acceptable results.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–6
 Table
Table2–7
2–7 Forecasting
ForecastingApproaches
Approaches

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–7
 Table
Table2–7
2–7 Forecasting
ForecastingApproaches
Approaches(cont’d)
(cont’d)

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–8
 Figure
Figure22–1
–1 Examples
ExamplesofofSimple
SimplePatterns
PatternsSometimes
SometimesFound
FoundininTime
Time
Series
SeriesData
Data

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–9
 Figure
Figure22–2
–2 Data
Datawith
withTrend
Trendand
andSeasonal
SeasonalVariations
Variations

Source: E. Turban, Jay Aronson, and Ting-Peng Liang, Decision Support Systems and Intelligence Systems, 7th ed. (Upper Saddle River, NJ: Prentice Hall, 2005), p. 109.
Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–10
 Figure
Figure22–3
–3 Averaging
AveragingApplied
AppliedtotoThree
ThreePossible
PossiblePatterns
Patterns

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–11
 Example
Example2-1
2-1

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–12
 Figure
Figure22–4
–4 AAMoving
MovingAverage
AverageForecast
ForecastTends
Tendsto
toSmooth
Smoothand
andLag
Lag
Changes
Changesininthe
theData
Data

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–13
 Figure
Figure22–5
–5 The
TheMore
MorePeriods
PeriodsininaaMoving
MovingAverage,
Average,the
theGreater
Greaterthe
the
Forecast
ForecastWill
WillLag
LagChanges
Changesininthe
theData
Data

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–14
 Example
Example2-2
2-2

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–15
 Exhibit
Exhibit2-1
2-1 Moving
MovingAverage
AverageInput
Inputand
andOutput
Output

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–16
 Exhibit
Exhibit2-2
2-2 Moving
MovingAverage
AveragePreparation
PreparationScreen
Screen

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–17
 Figure
Figure22–6
–6 Relative
RelativeWeights
WeightsininExponential
ExponentialSmoothing
Smoothing

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–18
 Figure
Figure22–7
–7 AASmall
SmallValue
Valueof
ofααWill
WillSmooth
SmoothMore
MoreThan
ThanaaLarger
LargerValue
Value

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–19
 Exhibit
Exhibit2-3
2-3 Exponential
ExponentialSmoothing
SmoothingInput,
Input,Output,
Output,and
andChart
Chart

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–20
 Exhibit
Exhibit2-4
2-4 Exponential
ExponentialSmoothing
SmoothingPreparation
PreparationWizard
Wizard

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–21
 Table
Table22–1
–1 Values
ValuesofofΣΣt,t,t2,
t2,and
andΣΣt2t2

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–22
 Example
Example2-3
2-3

Monthly demand for Dan’s Doughnuts Solution

over the past nine months for trays (six 1. The data seem to show an upward,
dozen per tray) of sugar doughnuts was roughly linear trend:
Mar 112
Apr 125
May 120
Jun 133
Jul 136
Aug 146
Sept 140
Oct 155
Nov 152

1. Plot the data to determine if a linear

trend equation is appropriate.
2. Obtain a trend equation.
3. Forecast demand for the next two
months.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–23
 Example
Example2-3
2-3(cont’d)
(cont’d)

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–24
 Exhibit
Exhibit22–5
–5 Data
Datafor
forLinear
LinearTrend/Regression
Trend/RegressionAnalysis
Analysis

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–25
 Exhibit
Exhibit22–6
–6 Scatter
ScatterPlot
PlotDevelopment
Development

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–26
 Exhibit
Exhibit22–7
–7 Scatter
ScatterPlot
Plot

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–27
 Exhibit
Exhibit22–8
–8 Scatter
ScatterPlot
PlotTitles,
Titles,Axes,
Axes,and
andLabels
Labels

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–28
 Exhibit
Exhibit22–9
–9 Scatter
ScatterDiagram
Diagram

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–29
 Exhibit
Exhibit22–10
–10 Scatter
ScatterDiagram
Diagram

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–30
 Exhibit
Exhibit22–11
–11 Regression
RegressionOutput
Output

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–31
 Example
Example2-4
2-4

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–32
 Example
Example2-4
2-4cont’d
cont’d

A plot of the actual data and predicted values is shown below.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–33
 Exhibit
Exhibit22–12
–12 Trend-Adjusted
Trend-AdjustedExponential
ExponentialSmoothing
Smoothing

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–34
 Figure
Figure22–8
–8 Naive
NaiveApproaches
Approacheswith
withSeasonality
Seasonality

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–35
 Example
Example2-5
2-5

The manager of a parking

lot has computed daily
relatives for the number of
cars per day for his lot. The
computations are repeated
here (about three weeks
are shown for illustration).
A seven-period centered
moving average is used
because there are seven
days (seasons) per week.

The estimated Friday

relative is 136 + 140 +
133 + 3 + 136. Relative
for other days can be
computed in a similar
manner. For example,
the estimated Monday
relative is 0.77 + 0.72 +
0.69/3 = 0.73

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–36
 Figure
Figure22–9
–9 AACentered
CenteredMoving
MovingAverage
AverageClosely
CloselyTracks
Tracksthe
theData
Data

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–37
 Example
Example2-6
2-6

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–38
 Exhibit
Exhibit22–13
–13 Seasonal
SeasonalRelative
RelativeComputations
Computations

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–39
 Explanatory
Explanatory Models
Models
• Simple Linear Regression
– A model of two variables thought to be related.
• Dependent variable: the variable to be forecasted.
• Independent variable is used to “explain” or predict the value
of the dependent variable.
• Using the regression approach
– Identify an independent variable or variables.
– Obtain a sample of at least 10 observations.
– Develop an equation.
– Identify any restrictions on predictions.
– Measure accuracy in a given forecast.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–40
 Table
Table22–2
–2 Data
Datafor
forRegression
RegressionProblem
Problem

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–41
 Figure
Figure22–10
–10 AALinear
LinearRelationship
RelationshipAppears
AppearstotoExist
Exist

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–42
 Table
Table22–2
–2 Calculations
Calculationsfor
forRegression
RegressionCoefficients
Coefficients

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–43
 Figure
Figure22–11
–11 Graph
GraphofofRegression
RegressionLine
Line

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–44
 Table
Table22–4
–4 Selected
SelectedValues
Valuesofoft.t.025 for n-2 Degrees of Freedom (df)
025 for n-2 Degrees of Freedom (df)

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–45
 Figure
Figure22–12
–12 The
TheConditional
ConditionalDistributions
Distributionsofofy’s
y’sAre
AreAssumed
Assumedto
tobe
be
Normal
Normal

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–46
 Regression
Regression Assumptions
Assumptions
• Normality
– For any given value of x, there is a distribution of possible y
values that has a mean equal to the expected value (i.e., y = a +
bx) and the distribution is normal.
• Homoscedasticity
– The conditional distributions for all values of x have the same
dispersion.
• Linearity.
– The requirement of uniform scatter also means that there should
not be any patterns around the line.
• Independence.
– Values of y should not be correlated over time. If they are, it may
be more appropriate to use a time series model.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–47
 Figure
Figure22–13
–13 The
TheScatter
Scatteraround
aroundthe
theLine
LineIsIsNot
NotUniform
Uniform

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–48
 Figure
Figure22–14
–14 There
ThereShould
ShouldNot
NotBe
BeAny
AnyPatterns
Patternsaround
aroundthe
theLine
Line

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–49
 Exhibit
Exhibit22–14
–14 Linear
LinearRegression-Explanatory
Regression-ExplanatoryModel
ModelOutput
Output

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–50
 Table
Table22–5
–5 Expansion
Expansionof
ofData
DataUsed
UsedininSimple
SimpleRegression
RegressionSection
Section

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–51
 Exhibit
Exhibit22–15
–15 Input
InputBox
Boxfor
forMultiple
MultipleRegression
Regression

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–52
 Exhibit
Exhibit22–16
–16 Multiple
MultipleRegression
RegressionOutput
Outputwith
withExcel
Excel

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–53
 Summarizing
Summarizing Forecast
Forecast Accuracy
Accuracy

• The mean absolute

deviation (MAD)
– measures the average
forecast error over a number
of periods, without regard to
the sign of the error:

• The mean squared error

(MSE)
– is the average squared error
experienced over a number
of periods.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–54
 Example
Example2-7
2-7

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–55
 Figure
Figure22–15
–15 Monitoring
MonitoringForecast
ForecastErrors
Errors

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–56
 Relative
Relative Measures
Measures of
of Forecast
Forecast Accuracy
Accuracy
• Percentage error (PE)
– for a given time series data
measures the percentage
point deviation of the
forecasted value from the
actual value.
• Mean percentage error
(MPE)
– measures the forecast bias
• Mean absolute percentage
error (MAPE)
– measures overall forecast
accuracy.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–57
 Example
Example2-8
2-8

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–58
 Example
Example2-8
2-8cont’d
cont’d

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–59
 Example
Example2-8
2-8cont’d
cont’d

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–60
 Tracking
Tracking Signal
Signal
• The tracking signal
– Is the ratio of cumulative forecast error at any point in time to the
corresponding MAD at that point in time.
– A value of a tracking signal that is beyond the action limits suggests the need
for corrective action.

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–61
 Example
Example2-9
2-9

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–62
 Exhibit
Exhibit2–17
2–17 Measuring
MeasuringForecast
ForecastAccuracy
AccuracyUsing
UsingMAD,
MAD,MSE,
MSE,MPE,
MPE,and
and
MAPE
MAPE

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–63
 Table
Table2–6
2–6 Comparison
ComparisonofofTypes
Typesof
ofForecasts
Forecasts

Copyright © 2007 The McGraw-Hill Companies. All rights reserved. McGraw-Hill/Irwin 2–64