PDF Forecasting, Principles & Practice, principles and -Standards and Practices for Forecasting - Forecasting Principles - Forecasting: principles and practice
Wait Loading...

PDF :1
PDF :2 PDF :3 PDF :4 PDF :5 PDF :6 PDF :7 PDF :8

Forecasting Principles Practice Leader Rob J Hyndman 23 25 September 2014 University of Western Australia robjhyndman uwa? Resources Slides Exercises Textbook Useful links robjhyndman uwa2017 Forecasting principles and practice Background 3? This

PDF Astrology Predicting Weather Earthquakes Bv Raman Byprthi Ebook reseau lesgrandsvoisins astrology predicting weather earthquakes b v raman pdf PDF Astrology Predicting Weather Earthquakes Bv Raman Jowjmvc Ebook staging daytoday co za astrology predicting weather earthquakes b v raman

PDF Astrology Predicting Weather Earthquakes Bv Raman Byprthi Ebook reseau lesgrandsvoisins astrology predicting weather earthquakes b v raman pdf PDF Astrology Predicting Weather Earthquakes Bv Raman DayToDay staging daytoday co za astrology predicting weather earthquakes b

PDF Forecasting with confidence Global home kpmg content dam forecasting with confidence pdf PDF Forecasting at scale PeerJ peerj preprints 3190 pdf PDF Socially aware Large scale Crowd Forecasting Stanford

- forecasting at scale
- facebook profit forecasting
- forecasting library
- time series forecasting for hourly data
- ml forecasting
- forecast facebook
- time series forecasting with prophet

PDF Essential English Book 1 Foreign Students Free Downloadrylsearchperce epizy essential english book 1 foreign students free download pdf PDF Essential English For Foreign Students Book Ii 2a Ce Eckersley publisher staging streamable essential english for foreign students book ii 2a

PDF Foreign aid, economic growth and efficiency development OECD oecd derec sweden foreignaid pdf PDF Does foreign aid contribute to or impeded economic growth? jois eu files 2 493 Yiew Lau pdf

- definition of foreign aid pdf
- what is foreign aid
- role of foreign aid in economic development
- does foreign aid promote economic development
- importance of foreign aid to developing countries pdf
- positive effects of foreign aid
- foreign aid and economic development
- negative impact of foreign aid pdf

1) The functions of money are A) medium of exchange and the ability to buy goods and services B) medium of exchange, unit of account, and means of Mar 25, 2011 (including on the World Wide Web) will destroy the integrity of the work and

- Testbank 1
- Testbank 3
- Foreign Currency Translation
- PRINCIPLES OF MACROECONOMICS TEST BANK Table of Contents
- THE ECONOMICS OF MONEY
- BANKING
- Test bank MULTIPLE CHOICE
- The Economics of Money
- Working with Foreign Currencies
- Nursery-Landscape CDE Test Bank B
- International Financial Management

eflawards2017 co uk d610142 foreign legions of the third Foreign Legions Of The Third Reich Belgium Great Britain Holland Italy And Spain By Littlejohn D Ebook Foreign Legions Of The Third Reich Belgium Great Britain Holland Italy And Spain By Littlejohn D currently available at eflawards2017 co uk for review

PDF Foreign Legions Of The Third Reich Vol 3 Kronoscode chap kronoscode foreign legions of the third reich vol 3 pdf PDF Foreign Legions Of The Third Reich Vol 3 Home Bfxzgvn Ebook cascoon devlab fi foreign

Feb 6, 2008 It is one of the more bizarre footnotes in the story of the Third Reich that it was defended It was not the smallest of the Reich's foreign legions foreign ambassadors and the historical opinions of Russia's experts Latvian

- Franco's Request to the Third Reich for Military Assistance
- The Latvian Legion
- The debate on the Latvian SS Volunteer Legion
- The “Vietnam Legion”
- West German
- Who's Who in Nazi Germany
- Nazi Conspiracy and Aggression
- The Place of Turkestan in the Foreign Political Strategy of Germany
- Forced and Slave Labor in Nazi-Dominated Europe
- Cars & Nazis

intended to provide a comprehen- sive introduction to forecasting methods and to present enough inform

George Athanasopoulos May 2012

- 1 Getting started 1
- 1 What can be forecast
- 2 Forecasting,
- planning and goals
- 3 Determining what to forecast
- 4 Forecasting data and methods
- 5 Some case studies
- 6 The basic steps in a forecasting task
- 7 The statistical forecasting perspective 1
- 8 Exercises
- 9 Further reading

2 The 2

forecaster’s toolbox Graphics

Some simple forecasting methods Transformations and adjustments Evaluating forecast accuracy

Prediction intervals

Exercises

- 3 Judgmental forecasts 3
- 1 Introduction
- 2 Beware of limitations
- 3 Key principles
- 4 The Delphi method
- 5 Forecasting by analogy
- 6 Scenario forecasting
- 7 New product forecasting 3
- 8 Judgmental adjustments 3
- 9 Further reading
- 3 3 4 5 6 9 11 12 12 12
- 13 13 18 23 25 28 33 37 38 39 39
- 41 41 42 42 45 47 48 48 49 51
- 4 Simple regression 4
- 1 The simple linear model
- 2 Least squares estimation
- 3 Regression and correlation
- 4 Evaluating the regression model
- 53 53 54 55 57

- 59 61 62 64 70 70 71
- 5 Multiple regression 5
- 1 Introduction to multiple linear regression 5
- 2 Some useful predictors
- 3 Selecting predictors
- 4 Residual diagnostics
- 5 Matrix formulation
- 6 Non-linear regression
- 7 Correlation,
- causation and forecasting
- 8 Exercises
- 9 Further reading
- 73 74 78 83 86 90 91 93 94 97
- 6 Time series decomposition 6
- 1 Time series components
- 2 Moving averages
- 3 Classical decomposition
- 4 X-12-ARIMA decomposition
- 5 STL decomposition
- 6 Forecasting with decomposition 6
- 7 Exercises
- 8 Further reading
- 99 99 103 108 110 111 113 114 115
- 7 Exponential smoothing 7
- 1 Simple exponential smoothing
- 2 Holt’s linear trend method
- 3 Exponential trend method
- 4 Damped trend methods
- 5 Holt-Winters seasonal method
- 6 A taxonomy of exponential smoothing methods
- 7 Innovations state space models for exponential smoothing 7
- 8 Exercises
- 9 Further reading
- 117 117 122 125 125 125 125 125 125 125
- 127 127 127 127 127 127 127 127 127 127 127 127
- 8 ARIMA models 8
- 1 Stationarity and differencing
- 2 Backshift notation
- 3 Autoregressive models
- 4 Moving average models
- 5 Non-seasonal ARIMA models
- 6 Estimation and order selection 8
- 7 ARIMA modelling in R
- 8 Forecasting
- 9 Seasonal ARIMA models
- 10 ARIMA vs ETS
- 11 Exercises

- 12 Further reading
- 127 9 Advanced forecasting methods 9
- 1 Dynamic regression models
- 2 Vector autoregressions
- 3 Neural network models
- 4 Forecasting hierarchical or grouped 9
- 5 Further reading
- 129 129 129 129 129 129

10 Data

11 Using R

- 12 Resources 12
- 1 R code for all chapters
- 2 Solutions to exercises
- 3 Time series course
- 4 Predictive Analytics course (University of Sydney)
- 5 Economic Forecasting course (University of Hawaii)
- 6 Test bank
- 7 Case study: Planning and forecasting in a volatile setting 13 Reviews
- 135 135 135 135 136 136 136 137 139

Australian quarterly beer production: 1992Q1–2008Q3

Monthly sales of antidiabetic drugs in Australia

Seasonal plot of monthly antidiabetic drug sales in Australia

Seasonal plot of monthly antidiabetic drug sales in Australia

Carbon footprint and fuel economy for cars made in 2009

- 82 from Anscombe (1973)

Autocorrelation function of quarterly beer production

Autocorrelation function for the white noise series

Power transformations for Australian monthly electricity data

Monthly milk production per cow

Forecasts of the Dow Jones Index from 16 July 1994

The Dow Jones Index measured daily to 15 July 1994

Residuals from forecasting the Dow Jones Index with the naïve method

- 13 14 15 16 17 18 20 20 21 22 22 23 24 25 26 28 30 31 34 35 35 35

Long run annual forecasts for domestic visitor nights for Australia

Estimated regression line for a random sample of size N

Fitted regression line from regressing the carbon footprint of cars versus their fuel economy in city driving conditions

- 4 Residual plot from regressing carbon footprint versus fuel economy in city driving conditions
- 5 The effect of outliers and influential observations on regression
- 6 Forecast with 80% and 95% forecast intervals for a car with x = 30 mpg in city driving
- 7 Fitting a log-log functional form to the Car data example
- 8 Residual plot from estimating a log-log functional form for the Car data example
- 9 The four non-linear forms shown in Table 4
- 10 Percentage changes in personal consumption expenditure for the US
- 11 Forecasting percentage changes in personal consumption expenditure for the US
- 56 57 58 60 63 63 64 65 66

- 12 Forecasting international tourist arrivals to Australia for the period 2011-2015 using a linear trend
- 13 Residuals from the regression models for Consumption and Tourism
- 14 Trending time series data can appear to be related

Time plot of beer production and predicted beer production

The residuals from the credit score model plotted against the fitted values obtained from the model

Residuals from the regression model for beer production

Cubic regression spline fitted to the fuel economy data

Electrical equipment orders

Seasonal sub-series plot of the seasonal component from the STL decomposition

Residential electricity sales for South Australia: 1989-2008

The electrical equipment orders and its three additive components obtained from a robust STL decomposition

- 11 Naïve forecasts of the seasonally adjusted data obtained from an STL decomposition 6
- 12 Forecasts of the electrical equipment orders data based on a naïve forecast of the seasonally adjusted data and a seasonal naïve forecast of the seasonal component,

after an an STL decomposition of the data

- 13 Decomposition of the number of persons in the civilian labor force in Australia each month from February 1978 to August 1995
- 67 68 69 74 75 76 78 81 81 82 87 88 88 89 92 92 100 101 102 102 103 104 105 106 108 112 113

114 115

- 118 Simple exponential smoothing applied to oil production in Saudi Arabia (1996–2007)
- 121 Forecasting Air Passengers in Australia (thousands of passengers)

List of Tables 1

- 106 Commonly used weights in weighted moving averages
- 118 Forecasting oil production for Saudi Arabia using simple exponential smoothing

This textbook is intended to provide a comprehensive introduction to forecasting methods and to present enough information about each method for readers to be able to use them sensibly

We don’t attempt to give a thorough discussion of the theoretical details behind each method,

although the references at the end of each chapter will fill in many of those details

The book is written for three audiences: (1) people finding themselves doing forecasting in business when they may not have had any formal training in the area

(2) undergraduate students studying business

(3) MBA students doing a forecasting elective

We use it ourselves for a second-year subject for students undertaking a Bachelor of Commerce degree at Monash University,

Australia

For most sections,

we only assume that readers are familiar with algebra,

and high school mathematics should be sufficient background

Readers who have completed an introductory course in statistics will probably want to skip some of Chapters 2 and 4

There are a couple of sections which require knowledge of matrices,

- but these are flagged

these lists comprise suggested textbooks that provide a more advanced or detailed treatment of the subject

we suggest journal articles that provide more information

We use R throughout the book and we intend students to learn how to forecast with R

- not just for forecasting

See Using R for instructions on installing and using R

The book is different from other forecasting textbooks in several ways

- • It is free and online,

making it accessible to a wide audience

- • It uses R,
- which is free,
- open-source,

and extremely powerful software

• It is continuously updated

You don’t have to wait until the next edition for errors to be removed or new methods to be discussed

• There are dozens of real data examples taken from our own consulting practice

and this experience has contributed directly to many of the examples given here,

as well as guiding our general philosophy of forecasting

• We emphasise graphical methods more than most forecasters

analyse the validity of the models fitted and present the forecasting results

feel free to add them on the book page

! Rob J Hyndman George Athanasopoulos May 2012

sometimes being considered a sign of divine inspiration,

and sometimes being seen as a criminal activity

The Jewish prophet Isaiah wrote in about 700 BC Tell us what the future holds,

so we may know that you are gods

(Isaiah 41:23) One hundred years later,

- in ancient Babylon,

forecasters would foretell the future based on the distribution of maggots in a rotten sheep’s liver

people wanting forecasts would journey to Delphi in Greece to consult the Oracle,

who would provide her predictions while intoxicated by ethylene vapours

who issued a decree in AD357 forbidding anyone “to consult a soothsayer,

- a mathematician,

or a forecaster May curiosity to foretell the future be silenced forever

” A similar ban on forecasting occurred in England in 1736 when it became an offence to defraud by charging money for predictions

! The varying fortunes of forecasters arise because good forecasts can seem almost magical,

while bad forecasts may be dangerous

• I think there is a world market for maybe five computers

- (Chairman of IBM,
- 1943) • Computers in the future may weigh no more than 1
- (Popular Mechanics,
- 1949) • There is no reason anyone would want a computer in their home
- (President,
- 1977) The last of these was made only three years before IBM produced the first personal computer

Not surprisingly,

you can no longer buy a DEC computer

Forecasting is obviously a difficult activity,

and businesses that do it well have a big advantage over those whose forecasts fail

we will explore the most reliable methods for producing forecasts

- and have been shown to work

Forecasting is required in many situations: deciding whether to build another power generation plant in the next five years requires forecasts of future demand

scheduling staff in a call centre next week requires forecasts of call volumes

stocking an inventory requires forecasts of stock requirements

Forecasts can be required several years in advance (for the case of capital investments),

or only a few minutes beforehand (for telecommunication routing)

forecasting is an important aid to effective and efficient planning

Some things are easier to forecast than others

On the other hand,

tomorrow’s lotto numbers cannot be forecast with any accuracy

The predictability of an event or a quantity depends on several factors including: 3

how well we understand the factors that contribute to it

- how much data are available

whether the forecasts can affect the thing we are trying to forecast

For example,

forecasts of electricity demand can be highly accurate because all three conditions are usually satisfied

We have a good idea on the contributing factors: electricity demand is driven largely by temperatures,

with smaller effects for calendar variation such as holidays,

- and economic conditions

Provided there is a sufficient history of data on electricity demand and weather conditions,

and we have the skills to develop a good model linking electricity demand and the key driver variables,

the forecasts can be remarkably accurate

On the other hand,

when forecasting currency exchange rates,

only one of the conditions is satisfied: there is plenty of available data

we have a very limited understanding of the factors that affect exchange rates,

and forecasts of the exchange rate have a direct effect on the rates themselves

then people will immediately adjust the price they are willing to pay and so the forecasts are selffulfilling

In a sense the exchange rates become their own forecasts

forecasting whether the exchange rate will rise or fall tomorrow is about as predictable as forecasting whether a tossed coin will come down as a head or a tail

you will be correct about 50 Often in forecasting,

a key step is knowing when something can be forecast accurately,

and when forecasts will be no better than tossing a coin

Good forecasts capture the genuine patterns and relationships which exist in the historical data,

but do not replicate past events that will not occur again

we will learn how to tell the difference between a random fluctuation in the past data that should be ignored,

and a genuine pattern that should be modelled and extrapolated

Every environment is changing,

and a good forecasting model captures the way in which things are changing

What is normally assumed is that the way in which the environment is changing will continue into the future

a highly volatile environment will continue to be highly volatile

a business with fluctuating sales will continue to have fluctuating sales

and an economy that has gone through booms and busts will continue to go through booms and busts

- not just where things are

As Abraham Lincoln said,

we could better judge what to do and how to do it"

factors determining actual outcomes,

- types of data patterns,
- and many other aspects

Forecasting methods can be very simple such as using the most recent observation as a forecast (which is called the "naïve method”),

or highly complex such as neural nets and econometric systems of simultaneous equations

there will be no data available at all

we may wish to forecast the sales of a new product in its first year,

but there are obviously no data to work with

In situations like this,

we use judgmental forecasting,

- discussed in Chapter 3

The choice of method depends on what data are available and the predictability of the quantity to be forecast

- planning and goals

where it helps to inform decisions about the scheduling of production,

- transportation and personnel,

and provides a guide to long-term strategic planning

However,

business forecasting is often done poorly,

and is frequently confused with planning and goals

They are three different things

Forecasting: principles and practice

is about predicting the future as accurately as possible,

given all of the information available,

including historical data and knowledge of any future events that might impact the forecasts

but this does not always occur

Too often,

goals are set without any plan for how to achieve them,

and no forecasts for whether they are realistic

Planning involves determining the appropriate actions that are required to make your forecasts match your goals

as it can play an important role in many areas of a company

Modern organizations require short-term,

medium-term and long-term forecasts,

depending on the specific application

Short-term forecasts are needed for the scheduling of personnel,

- production and transportation

As part of the scheduling process,

forecasts of demand are often also required

in order to purchase raw materials,

- hire personnel,

or buy machinery and equipment

Such decisions must take account of market opportunities,

environmental factors and internal resources

An organization needs to develop a forecasting system that involves several approaches to predicting uncertain events

applying a range of forecasting methods,

selecting appropriate methods for each problem,

and evaluating and refining forecasting methods over time

It is also important to have strong organizational support for the use of formal forecasting methods if they are to be used successfully

decisions need to be made about what should be forecast

For example,

if forecasts are required for items in a manufacturing environment,

it is necessary to ask whether forecasts are needed for: 1

- every product line,
- or for groups of products
- every sales outlet,

or for outlets grouped by region,

- or only for total sales
- weekly data,
- monthly data or annual data

? It is also necessary to consider the forecasting horizon

Will forecasts be required for one month in advance,

- for 6 months,
- or for ten years

? Different types of models will be necessary,

depending on what forecast horizon is most important

? Forecasts that need to be produced frequently are better done using an automated system than with methods that require careful manual work

Forecasting: principles and practice

It is worth spending time talking to the people who will use the forecasts to ensure that you understand their needs,

and how the forecasts are to be used,

before embarking on extensive work in producing the forecasts

it is then necessary to find or collect the data on which the forecasts will be based

a lot of data are recorded and the forecaster’s task is often to identify where and how the required data are stored

the historical demand for a product,

or the unemployment rate for a geographical region

A large part of a forecaster’s time can be spent in locating and collating the available data prior to developing suitable forecasting methods

or if the data available are not relevant to the forecasts,

then qualitative forecasting methods must be used

These methods are not purely guesswork—there are well-developed structured approaches to obtaining good forecasts without using historical data

numerical information about the past is available

it is reasonable to assume that some aspects of the past patterns will continue into the future

There is a wide range of quantitative forecasting methods,

often developed within specific disciplines for specific purposes

Each method has its own properties,

- accuracies,

and costs that must be considered when choosing a specific method

Most quantitative forecasting problems use either time series data (collected at regular intervals over time) or cross-sectional data (collected at a single point in time)

we are wanting to predict the value of something we have not observed,

using the information on the cases that we have observed

Examples of cross-sectional data include: • House prices for all houses sold in 2011 in a particular area

We are interested in predicting the price of a house not in our data set using various house characteristics: position,

- bedrooms,

• Fuel economy data for a range of 2009 model cars

We are interested in predicting the carbon footprint of a vehicle not in our data set using information such as the size of the engine and the fuel efficiency of the car

- 1 Car emissions Table 1
- 1 gives some data on 2009 model cars,

each of which has an automatic transmission,

four cylinders and an engine size under 2 liters

Engine (litres) 1

- 3 40 45 Honda Fit 1
- 5 27 33 Honda Fit 1
- 5 28 35 Hyundai Accent 1
- 6 26 35 Kia Rio 1
- 6 26 35 Nissan Versa 1
- 8 27 33 Nissan Versa 1
- 8 24 32 Pontiac G3 Wave 1
- 6 25 34 Pontiac G3 Wave 5 1
- 6 25 34 Pontiac Vibe 1
- 8 26 31 Saturn Astra 2DR 1
- 8 24 30 Hatchback Saturn Astra 4DR 1
- 8 24 30 Hatchback Scion xD 1
- 8 26 32 Toyota Corolla 1
- 8 27 35 Toyota Matrix 1
- 8 25 31 Toyota Prius 1
- 5 48 45 Toyota Yaris 1
- 5 29 35 Table 1
- 1: Fuel economy and carbon footprints for 2009 model cars with automatic transmissions,

four cylinders and small engines

A forecaster may wish to predict the carbon footprint (tons of CO2 per year) for other similar vehicles that are not included in the above table

It is necessary to first estimate the effects of the predictors (number of cylinders,

- size of engine,

and fuel economy) on the variable to be forecast (carbon footprint)

provided that we know the predictors for a car not in the table,

we can forecast its carbon footprint

Cross-sectional models are used when the variable to be forecast exhibits a relationship with one or more other predictor variables

The purpose of the cross-sectional model is to describe the form of the relationship and use it to forecast values of the forecast variable that have not been observed

any change in predictors will affect the output of the system in a predictable way,

assuming that the relationship does not change

Models in this class include regression models,

- additive models,

and some kinds of neural networks

Some people use the term "predict" for cross-sectional data and "forecast" for time series data (see below)

In this book,

we will not make this distinction—we will use the words interchangeably

Time series forecasting Time series data are useful when you are forecasting something that is changing over time (e

- stock prices,
- sales figures,
- profits,

Examples of time series data include: • Daily IBM stock prices • Monthly rainfall • Quarterly sales results for Amazon • Annual Google profits

Forecasting: principles and practice

we will only consider time series that are observed at regular intervals of time (e

- hourly,
- weekly,
- monthly,
- quarterly,
- annually)

but are beyond the scope of this book

the aim is to estimate how the sequence of observations will continue into the future

The following figure shows the quarterly Australian beer production from 1992 to the third quarter of 2008

Figure 1

- 1: Australian quarterly beer production: 1992Q1–2008Q3,
- with two years of forecasts

Notice how the forecasts have captured the seasonal pattern seen in the historical data and replicated it for the next two years

The dark shaded region shows 80% prediction intervals

each future value is expected to lie in the dark blue region with a probability of 80%

These prediction intervals are a very useful way of displaying the uncertainty in forecasts

In this case,

the forecasts are expected to be very accurate,

hence the prediction intervals are quite narrow

and makes no attempt to discover the factors which affect its behavior

but it ignores all other information such as marketing initiatives,

- competitor activity,

changes in economic conditions,

- and so on

exponential smoothing and structural models

Predictor variables and time series forecasting Predictor variables can also be used in time series forecasting

suppose we wish to forecast the hourly electricity demand (ED) of a hot region during the summer period

A model with predictor variables might be of the form ED = f (current temperature,

- strength of economy,
- population,
- time of day,
- day of week,

The relationship is not exact—there will always be changes in electricity demand that cannot be accounted for by the predictor variables

The “error” term on the right allows for random variation and the effects of relevant variables that are not included in the model

We call this an “explanatory model” because it helps explain what causes the variation in electricity demand

Forecasting: principles and practice

Because the electricity demand data form a time series,

we could also use a time series model for forecasting

a suitable time series forecasting equation is of the form EDt+1 = f (EDt ,

- error),
- where t is the present hour,
- t + 1 is the next hour,
- t − 1 is the previous hour,
- t − 2 is two hours ago,
- and so on

prediction of the future is based on past values of a variable,

but not on external variables which may affect the system

the "error" term on the right allows for random variation and the effects of relevant variables that are not included in the model

it might be given by EDt+1 = f (EDt ,

- current temperature,
- time of day,
- day of week,

They are known as dynamic regression models,

- panel data models,
- longitudinal models,
- transfer function models,

and linear system models (assuming f is linear)

These models are discussed in Chapter 9

rather than only historical values of the variable to be forecast

However,

there are several reasons a forecaster might select a time series model rather than an explanatory model

the system may not be understood,

and even if it was understood it may be extremely difficult to measure the relationships that are assumed to govern its behavior

Second,

it is necessary to know or forecast the various predictors in order to be able to forecast the variable of interest,

- and this may be too difficult

the main concern may be only to predict what will happen,

- not to know why it happens

the time series model may give more accurate forecasts than an explanatory or mixed model

the accuracy of the competing models,

and how the forecasting model is to be used

we will use the subscript i to indicate a specific observation

yi will denote the ith observation in a data set

we will use the subscript t instead of i

For example,

yt will denote the observation at time t

When we are making general comments that could be applicable to either cross-sectional or time series data,

- we will tend to use i and N

Some case studies

The following four cases are from our consulting practice and demonstrate different types of forecasting situations and the associated problems that often arise

Case 1 The client was a large company manufacturing disposable tableware such as napkins and paper plates

They needed forecasts of each of hundreds of items every month

The time series data showed a range of patterns,

- some with trends,
- some seasonal,
- and some with neither

they were using their own software,

- written in-house,

but it often produced forecasts that did not seem sensible

average of the last 12 months data

average of the last 6 months data

prediction from a straight line regression over the last 12 months

prediction from a straight line regression over the last 6 months

prediction obtained by a straight line through the last observation with slope equal to the average slope of the lines connecting last year’s and this year’s values

prediction obtained by a straight line through the last observation with slope equal to the average slope of the lines connecting last year’s and this year’s values,

where the average is taken only over the last 6 months

They required us to tell them what was going wrong and to modify the software to provide more accurate forecasts

The software was written in COBOL making it difficult to do any sophisticated numerical computation

Case 2 In this case,

the client was the Australian federal government who needed to forecast the annual budget for the Pharmaceutical Benefit Scheme (PBS)

and the expenditure depends on what people purchase during the year

The total expenditure was around A$7 billion in 2009 and had been underestimated by nearly $1 billion in each of the two years before we were asked to assist with developing a more accurate forecasting approach

it is necessary to forecast the sales volumes of hundreds of groups of pharmaceutical products using monthly data

Almost all of the groups have trends and seasonal patterns

The sales volumes for many groups have sudden jumps up or down due to changes in what drugs are subsidised

The expenditures for many groups also have sudden changes due to cheaper competitor drugs becoming available

Thus we needed to find a forecasting method that allowed for trend and seasonality if they were present,

and at the same time was robust to sudden changes in the underlying patterns

lease them out for three years,

- and then sell them

understanding what affects resale values may allow leasing and sales policies to be developed in order to maximize profits

the resale values were being forecast by a group of specialists

they saw any statistical model as a threat to their jobs and were uncooperative in providing information

Nevertheless,

the company provided a large amount of data on previous vehicles and their eventual resale values

we needed to develop a model for forecasting weekly air passenger traffic on major domestic routes for one of Australia’s leading airlines

The company required forecasts of passenger numbers for each major domestic route and for each class of passenger (economy class,

business class and first class)

The company provided weekly traffic data from the previous six years

- major sporting events,
- advertising campaigns,
- competition behaviour,

and sporting events sometimes move from one city to another

During the period of the

- historical data,

there was a major pilots’ strike during which there was no traffic for several months

the airline had trialled a redistribution of some economy class seats to business class,

and some business class seats to first class

After several months,

- however,

the seat classifications reverted to the original distribution

The basic steps in a forecasting task

A forecasting task usually involves five basic steps

Step 1: Problem definition

- who requires the forecasts,

and how the forecasting function fits within the organization requiring the forecasts

- maintaining databases,

and using the forecasts for future planning

Step 2: Gathering information

There are always at least two kinds of information required: (a) statistical data,

and (b) the accumulated expertise of the people who collect the data and use the forecasts

it will be difficult to obtain enough historical data to be able to fit a good statistical model

- occasionally,

very old data will be less useful due to changes in the system being forecast

Step 3: Preliminary (exploratory) analysis

Always start by graphing the data

? Is there a significant trend

- ? Is seasonality important

? Is there evidence of the presence of business cycles

? Are there any outliers in the data that need to be explained by those with expert knowledge

? How strong are the relationships among the variables available for analysis

? Various tools have been developed to help with this analysis

The best model to use depends on the availability of historical data,

the strength of relationships between the forecast variable and any explanatory variables,

and the way the forecasts are to be used

Each model is itself an artificial construct that is based on a set of assumptions (explicit and implicit) and usually involves one or more parameters which must be "fitted" using the known historical data

exponential smoothing methods (Chapter 7),

and a variety of other topics including dynamic regression models,

- neural networks,

and vector autoregression in Chapter 9

Once a model has been selected and its parameters estimated,

the model is used to make forecasts

The performance of the model can only be properly evaluated after the data for the forecast period have become available

There are also organizational issues in using and acting on the forecasts

A brief discussion of some of these issues is in Chapter 2

The statistical forecasting perspective

and so we can think of it as a random variable

the total sales for next month could take a range of possible values,

and until we add up the actual sales at the end of the month we don’t know what the value will be

until we know the sales for next month,

- it is a random quantity

Because next month is relatively close,

we usually have a good idea what the likely sales values could be

if we are forecasting the sales for the same month next year,

the possible values it could take are much more variable

In most forecasting situations,

the variation associated with the thing we are forecasting will shrink as the event approaches

the further ahead we forecast,

- the more uncertain we are

we are estimating the middle of the range of possible values the random variable could take

a forecast is accompanied by a prediction interval giving a range of values the random variable could take with relatively high probability

For example,

a 95% prediction interval contains a range of values which should include the actual future value with probability 95%

A forecast is always based on some observations

We then write yi|I meaning "the random variable yi given what we know in I"

along with their relative probabilities,

is known as the "probability distribution" of yi|I

we call this the "forecast distribution"

we usually mean the average value of the forecast distribution,

and we put a "hat" over yy to show this

we write the forecast of yi as yˆi ,

meaning the average of the possible values that yi could take given everything we know

Occasionally,

we will use yˆi to refer to the median (or middle value) of the forecast distribution instead

With time series forecasting,

it is often useful to specify exactly what information we have used in calculating the forecast

Then we will write,

- for example,

yˆt|t−1 to mean the forecast of yt taking account of all previous observations (y1 ,

- yt−1 )

Similarly,

an h-step forecast taking account of all observations up to time T )

Exercises

what sort of data is involved: time series or cross-sectional data

list the possible predictor variables that might be useful,

assuming that the relevant data are available

describe the five steps of forecasting in the context of this project

- • Armstrong,

MA: Kluwer Academic Publishers

- • Ord,

it is necessary to build a toolbox of techniques that will be useful for many different forecasting situations

Each of the tools discussed in this chapter will be used repeatedly in subsequent chapters as we develop and explore a range of forecasting methods

- unusual observations,
- changes over time,

and relationships between variables

The features that are seen in plots of the data must then be incorporated,

- as far as possible,

into the forecasting methods to be used

it also determines what graphs are appropriate

Time plots For time series data,

the obvious graph to start with is a time plot

the observations are plotted against the time of observation,

with consecutive observations joined by straight lines

The figure below shows the weekly economy passenger load on Ansett Airlines between Australia’s two largest cities

Figure 2

- 1: Weekly economy passenger load on Ansett Airlines 13

Forecasting: principles and practice Listing 2

- 1: R code plot ( melsyd [ ,
- " Economy

C l'a s's " ] ,

main=" Economy␣ c'l'a s's ␣ p a s's e n g e r s': ␣ Melbourne−Sydney " ,

- x l'a b=" Year " ,
- y l'a b=" Thousands " )

The time plot immediately reveals some interesting features

• There was a period in 1989 when no passengers were carried — this was due to an industrial dispute

• There was a period of reduced load in 1992

This was due to a trial in which some economy class seats were replaced by business class seats

• A large increase in passenger load occurred in the second half of 1991

• There are some large dips in load around the start of each year

• There is a long-term fluctuation in the level of the series which increases during 1987,

decreases in 1989 and increases again through 1990 and 1991

• There are some periods of missing observations

Any model will need to take account of all these features in order to effectively forecast the passenger load into the future

- 2: Monthly sales of antidiabetic drugs in Australia Listing 2
- 2: R code plot ( a10 ,

y l'a b=" \$␣ m i l'l i o n " ,

- x l'a b=" Year " ,

main=" A n t i d'i a b e t i c'␣ drug ␣ s'a l'e s'" )

The sudden drop at the end of each year is caused by a government subsidisation scheme that makes it cost-effective for patients to stockpile drugs at the end of the calendar year

and the fact that the trend is changing slowly

Time series patterns In describing these time series,

we have used words such as "trend" and "seasonal" which need to be more carefully defined

• A trend exists when there is a long-term increase or decrease in the data

• A seasonal pattern occurs when a time series is affected by seasonal factors such as the time of the year or the day of the week

The monthly sales of antidiabetic drugs above shows seasonality partly induced by the change in cost of the drugs at the end of the calendar year

• A cycle occurs when the data exhibit rises and falls that are not of a fixed period

These fluctuations are usually due to economic conditions and are often related to the "business cycle"

Seasonal patterns have a fixed and known length,

while cyclic patterns have variable and unknown length

and the magnitude of cyclic variation is usually more variable than that of seasonal variation

- cycles and seasonality

we will first need to identify the time series patterns in the data,

and then choose a method that is able to capture the patterns properly

Seasonal plots A seasonal plot is similar to a time plot except that the data are plotted against the individual "seasons" in which the data were observed

- 3: Seasonal plot of monthly antidiabetic drug sales in Australia

Forecasting: principles and practice Listing 2

- 3: R code s'e a s'o n p l'o t ( a10 ,

y l'a b=" \$␣ m i l'l i o n " ,

- x l'a b=" Year " ,

main=" S e a s'o n a l'␣ p l'o t : ␣ a n t i d'i a b e t i c'␣ drug ␣ s'a l'e s'" ,

- y e a r
- l'a b e l's=TRUE,
- y e a r
- l'a b e l's
- l'e f t =TRUE,
- c o l'=1:20 ,
- pch =19)

but now the data from each season are overlapped

and is especially useful in identifying years in which the pattern changes

it is clear that there is a large jump in sales in January each year

these are probably sales in late December as customers stockpile before the end of the calendar year,

but the sales are not registered with the government until a week or two later

The graph also shows that there was an unusually low number of sales in March 2008 (most other years show an increase between February and March)

The small number of sales in June 2008 is probably due to incomplete counting of sales at the time the data were collected

Seasonal subseries plots An alternative plot that emphasises the seasonal patterns is where the data for each season are collected together in separate mini time plots

- 4: Seasonal plot of monthly antidiabetic drug sales in Australia

- 4: R code monthplot ( a10 ,

y l'a b=" \$␣ m i l'l i o n " ,

- x l'a b=" Month " ,
- xaxt=" n " ,

main=" S e a s'o n a l'␣ d'e v i a t i o n ␣ p l'o t : ␣ a n t i d'i a b e t i c'␣ drug ␣ s'a l'e s'" ) axis ( 1 ,

- a t =1:12 ,
- l a b e l's=month

This form of plot enables the underlying seasonal pattern to be seen clearly,

and also shows the changes in seasonality over time

It is especially useful in identifying changes within particular seasons

In this example,

the plot is not particularly revealing

- but in some cases,

this is the most useful way of viewing seasonal changes over time

Scatterplots are most useful for exploring relationships between variables in cross-sectional data

The figure below shows the relationship between the carbon footprint and fuel economy for small cars (using an extension of the data set shown in Section 1

Each point on the graph shows one type of vehicle

- 5: Carbon footprint and fuel economy for cars made in 2009

Listing 2

- 5: R code plot ( j i t t e r ( f u e l'[ ,

5 ] ) ,

- j i t t e r ( f u e l'[ ,

8 ] ) ,

- x l'a b=" City ␣mpg" ,

y l'a b=" Carbon ␣ f o o t p r i n t " )

There is a strong non-linear relationship between the size of a car’s carbon footprint and its city-based fuel economy

Vehicles with better fuel-economy have a smaller carbon-footprint than vehicles that use a lot of fuel

the relationship is not linear — there is much less benefit in improving fuel-economy from 30 to 40 mpg than there was in moving from 20 to 30 mpg

knowing the fuel economy of the car will allow a relatively accurate forecast of its carbon footprint

and suggests that a forecasting model must include fuel-economy as a predictor variable

Some of the other information we know about these cars may also be helpful in improving the forecasts

it is useful to plot each variable against each other variable

These plots can be arranged in a scatterplot matrix,

- as shown in Figure 2

Listing 2

- 6: R code pairs ( f u e l'[ ,
- − c'( 1 : 2 ,

7 ) ] ,

- pch =19)

For each panel,

the variable on the vertical axis is given by the variable name in that row,

and the variable on the horizontal axis is given by the variable name in that column

the graph of carbon-footprint against city mpg is shown on the bottom row,

- second from the left

The value of the scatterplot matrix is that it enables a quick view of the relationships between all pairs of variables

Outliers can also be seen

there are two vehicles that have very high highway mileage,

small engines and low carbon footprints

Forecasting: principles and practice