Time Series and Forecasting

Chapter 16

McGraw-Hill/Irwin Copyright © 2010 by The McGraw-Hill Companies, Inc. All rights reserved.
 Goals

1. Define the components of a time series

2. Compute moving average
3. Determine a linear trend equation
4. Compute a trend equation for a nonlinear trend
5. Use a trend equation to forecast future time periods
and to develop seasonally adjusted forecasts
6. Determine and interpret a set of seasonal indexes
7. Deseasonalize data using a seasonal index
8. Test for autocorrelation

16-2
 Time Series and its Components
TIME SERIES is a collection of data recorded
over a period of time (weekly, monthly,
quarterly), an analysis of history, that can be
used by management to make current
decisions and plans based on long-term
forecasting. It usually assumes past pattern
to continue into the future

Components of a Time Series

1. Secular Trend – the smooth long term

direction of a time series

2. Cyclical Variation – the rise and fall of

a time series over periods longer than
one year

3. Seasonal Variation – Patterns of

change in a time series within a year
which tends to repeat each year

4. Irregular Variation – classified into:

Episodic – unpredictable but
identifiable
Residual – also called chance
fluctuation and unidentifiable
16-3
 The Moving Average Method
 Useful in smoothing time series to see its trend
 Basic method used in measuring seasonal fluctuation
 Applicable when time series follows fairly linear trend that have definite rhythmic pattern

16-4
 Weighted Moving Average
 A simple moving average assigns
the same weight to each
observation in averaging
 Weighted moving average assigns
different weights to each
observation
 Most recent observation receives
the most weight, and the weight
decreases for older data values
 In either case, the sum of the
weights = 1

Cedar Fair operates seven amusement

parks and five separately gated
water parks. Its combined
attendance (in thousands) for the
last 12 years is given in the
following table. A partner asks you
to study the trend in attendance.
Compute a three-year moving
average and a three-year
weighted moving average with
weights of 0.2, 0.3, and 0.5 for
successive years.
16-5
 Moving Average vs Weighted
Moving Average
 Moving Average vs Weighted Moving Average

 1. **Moving Average (MA)**:

 - Assigns equal weight to all observations in the time series.
 - Formula:
 SMA = (X1 + X2 + ... + Xn) / n
 - Example: 3-period moving average.
 - First average: (15 + 18 + 22) / 3 = 18.33
 - Second average: (18 + 22 + 24) / 3 = 21.33

 2. **Weighted Moving Average (WMA)**:

 - Assigns different weights to observations, with more weight given to recent data.
 - Formula:
 WMA = (w1 * X1 + w2 * X2 + ... + wn * Xn) / (w1 + w2 + ... + wn)
 - Example: 3-period weighted moving average with weights 0.5, 0.3, 0.2.
 - First weighted average: 17.3
 - Second weighted average: 20.4

16-6
 Linear Trend
 The long term trend of many business series often approximates a straight line

Linear Trend Equation : Y a  bt
where :

Y  read "Y hat" , is the projected value of the Y
variable for a selected value of t

a  the Y - intercept
(estimated value of Y when t 0 )

b  the slope of the line

(average change in Y for each unit change in t )

t  any value of time (coded) that is selected

•Use the least squares method in Simple Linear Regression (Chapter 13) to find the best linear relationship
between 2 variables
•Code time (t) and use it as the independent variable
•E.g. let t be 1 for the first year, 2 for the second, and so on (if data are annual)

16-7
 Linear Trend – Using the Least Squares
Method: An Example
The sales of Jensen Foods, a small grocery chain located in southwest Texas, since 2005 are:

Sales
Year t ($ mil.)

2005 1 7
2006 2 10
2007 3 9
2008 4 11
2009 5 13

16-8
 Nonlinear Trends
 A linear trend equation is used when the
data are increasing (or decreasing) by
equal amounts
 A nonlinear trend equation is used when
the data are increasing (or decreasing) by
increasing amounts over time
 When data increase (or decrease) by equal
percents or proportions plot will show
curvilinear pattern

 Top graph is original data

 Graph on bottom right is the log base 10 of
the original data which now is linear
(Excel function: Y = log(x) or log(x,10)
 Using Data Analysis in Excel, generate the
linear equation
 Regression output shown in next slide

16-9
 Log Trend Equation – Gulf Shores Importers
Example

The Linear Equation is :


y 2.053805  0.153357t

16-10
 Log Trend Equation – Gulf Shores
Importers Example

Estimate the Import for the year 2013 using the linear tre nd

y 2.053807  0.153357t
Substitute into the linear equation above the code (19) for 2013

y 2.053805  0.153357(19)

y 4.967588
 ^
Y
Then find the antilog of y 10
10 4.967588
92,809

16-11
 Seasonal Variation and Seasonal Index
 One of the components of a time series
 Seasonal variations are fluctuations that
coincide with certain seasons and are
repeated year after year
 Understanding seasonal fluctuations help
plan for sufficient goods and materials on
hand to meet varying seasonal demand
 Analysis of seasonal fluctuations over a
period of years help in evaluating current
sales

SEASONAL INDEX
 A number, usually expressed in percent,
that expresses the relative value of a
season with respect to the average for
the year (100%)
 Ratio-to-moving-average method
– The method most commonly used
to compute the typical seasonal
pattern
– It eliminates the trend (T), cyclical
(C), and irregular (I) components
from the time series

16-12
 Seasonal Index – An Example
EXAMPLE
The table below shows the quarterly sales for Toys
International for the years 2001 through 2006.
The sales are reported in millions of dollars.
Determine a quarterly seasonal index using the
ratio-to-moving-average method.

Step (1) – Organize time series data in column form

Step (2) Compute the 4-quarter moving totals
Step (3) Compute the 4-quarter moving averages
Step (4) Compute the centered moving averages by
getting the average of two 4-quarter moving
averages
Step (5) Compute ratio by dividing actual sales by the
centered moving averages

16-13
 Seasonal Index – An Example

16-14
 FORMULA FOR SEASONAL INDEX

 4-Quarter Moving Total (Winter for Q1 2002):

=B2+B3+B4+B5
 4-Quarter Moving Average (Winter for Q1
2002): =Moving Total/4
 Centered Moving Average:
=AVERAGE(Moving Average Q1, Moving
Average Q2)
 Seasonal Index: =Actual Sales / Centered
Moving Average

16-15
 Actual versus Deseasonalized Sales for
Toys International
Deseasonalized Sales = Sales / Seasonal Index

16-16
 Seasonal Index – An Example Using
Excel
Given the deseasonalized linear equation for Toys International sales as Ŷ=8.109 + 0.0899t, generate the seasonally
adjusted forecast for each of the quarters of 2010

Ŷ X SI = 10.62648 X 1.519
16-17
Ŷ = 8.10 + 0.0899(28)