Documentos de Académico
Documentos de Profesional
Documentos de Cultura
Introduction
Subjects of Forecasts
Prerequisites for a Good Forecast
Forecasting Techniques
Expert Opinion
Surveys and market research
Surveys of spending plans
Economic indicators
Projections
Econometric models
Introduction
Consumer intentions
Survey of Consumers, Survey Research Center,
University of Michigan
Consumer Confidence Survey, The Conference
Board
Surveys of Spending Plans
Surveys of spending plans seek
information about “macro-type” data
relating to the economy.
E = B(1+i)n
i = (E/B)1/n –1
Compound Growth Rate
Then project this constant growth rate
forward.
E = B(1+i)n
E = projection n = years (series +
projection)
B = beginning value
Projections
Time series forecasting: A naïve
method of forecasting from past data
by using least squares statistical
methods.
A time series analysis usually examines
•Trends
•Cyclical fluctuations
•Seasonal fluctuations
•Irregular movements.
Time Series Projections
Advantages
1. easy to calculate
2. does not require much judgment or
analytical skill
3. describes the best possible fit for past
data
4. usually reasonably reliable in the short
run
Time Series Projections
Yt = f(Tt, Ct, St, Rt)
Causal Models:
Explores cause-and-effect relationships
Uses leading indicators to predict the future
E.g. housing starts and appliance sales
Composition
of Time Series Data
Data = historic pattern + random
variation
Historic pattern may include:
Level (long-term average)
Trend
Seasonality
Cycle
Time Series Patterns
Methods of Forecasting the Level
Naïve Forecasting
Simple Mean
Moving Average
Weighted Moving Average
Exponential Smoothing
Time Series Problem
Determine forecast for Period Orders
periods 11 1 122
Naïve forecast 2 91
3 100
Simple average
4 77
3- and 5-period moving 5 115
average 6 58
3-period weighted moving 7 75
average with weights 0.5, 8 128
0.3, and 0.2 9 111
10 88
Exponential smoothing
11
with alpha=0.2 and 0.5
Time Chart of Orders Data
140
120
100
80
60
40
20
0
1 2 3 4 5 6 7 8 9 10
Naïve Forecasting
Next period forecast = Last Period’s
actual:
Ft 1 At
Simple Average (Mean)
Next period’s forecast = average of all
historical data
At At 1 At 2 .............
Ft 1
n
Moving Average
Next period’s forecast = simple average
of the last N periods
At At 1 ......... At N 1
Ft 1
N
The Effect of the Parameter N
A smaller N makes the forecast more
responsive
A larger N makes the forecast more
stable
Weighted Moving Average
Ft 1 C1 At C2 At 1 ......... C N At N 1
where
C1 C2 .........C N 1
Exponential Smoothing
Ft 1 At 1 Ft
where
0 1
The Effect of the Parameter
A smaller makes the forecast more
stable
A larger makes the forecast more
responsive
Time Series Problem Solution
11 88 97 109 92 103 99 98
Forecast Accuracy
Forecasts are rarely perfect
Need to know how much we should rely on
our chosen forecasting method
Measuring forecast error:
Et At Ft
Note that over-forecasts = negative errors
and under-forecasts = positive errors
Tracking Forecast Error
Over Time
Mean Absolute Deviation (MAD):
A good measure of the actual error
MAD
actual forecast
in a forecast n
Tracking Signal
Exposes bias (positive or negative) actual - forecast
TS
MAD
Accuracy & Tracking Signal Problem: A company is comparing the
accuracy of two forecasting methods. Forecasts using both methods are
shown below along with the actual values for January through May. The
company also uses a tracking signal with ±4 limits to decide when a
forecast should be reviewed. Which forecasting method is best?
Method A Method B
Month Actual F’cast Error Cum. Tracking F’cast Error Cum. Tracking
sales Signal Error Signal
Error
Jan. 30 28 2 2 2 28 2 2 1
Feb. 26 25 1 3 3 25 1 3 1.5
March 32 32 0 3 3 29 3 6 3
April 29 30 -1 2 2 27 2 8 4
May 31 30 1 3 3 29 2 10 5
MAD 1 2
MSE 1.4 4.4
Forecasting Trends
Trend-adjusted exponential smoothing
Three step process:
Smooth the level of the series:
St At (1 )( St 1 Tt 1 )
Smooth the trend:
Tt (St St 1 ) (1 )Tt 1
Calculate the forecast including trend:
FITt 1 St Tt
Forecasting trend problem: a company uses exponential smoothing with trend to
forecast usage of its lawn care products. At the end of July the company wishes to
forecast sales for August. July demand was 62. The trend through June has been 15
additional gallons of product sold per month. Average sales have been 57 gallons
per month. The company uses alpha+0.2 and beta +0.10. Forecast for August.
line
b
XY n X Y
X nX
2 2
b
XY n X Y
Sales $ Adv.$ XY X^2 Y^2
X nX 2 2
(Y) (X)
1 130 48 4240 2304 16,900 30282 451.25147.25
b 3.58
2 151 52 7852 2704 22,801 10533 451.25
2
n XY X Y
r
X X Y Y
2 2
2 2
n * n
(4)30,282 (205)589
r .888
4(10,533) - (205) * 487,165 589
2 2
r 2 .982 .788
2
2
Coefficient of determination ( r ) measures the amount of variation in the
dependent variable about its mean that is explained by the regression line.
2
Values of ( r ) close to 1.0 are desirable.
Factors for Selecting a
Forecasting Model
The amount & type of available data
Degree of accuracy required
Length of forecast horizon
Presence of data patterns
Forecasting Software
Spreadsheets
Microsoft Excel, Quattro Pro, Lotus 1-2-3
Limited statistical analysis of forecast data
Statistical packages
SPSS, SAS, NCSS, Minitab
Forecasting plus statistical and graphics
Specialty forecasting packages
Forecast Master, Forecast Pro, Autobox, SCA