Time Series Analysis and Forecasting by Example

by Bisgaard, Sø; ren; Kulahci, Murat

• ISBN13: 9780470540640
• ISBN10: 0470540648
• Edition: 1st
• Format: Hardcover
• Copyright: 2011-08-09
• Publisher: Wiley

Summary

Times Series Analysis and Forecasting presents seemingly difficult techniques and methodologies in an insightful and application-based way. Through a hands-on and user-friendly approach, this text includes exercises, graphical techniques, examples, excel spreadsheets, and software applications on time series analysis. The reference offers step-by-step procedures and instructions. This textbook is essential for students, emphasizing intuitive learning rather than theory through modeling the data in careful interpretation and use of modern statistical graphics.

Author Biography

The late Soren Bisgaard, PHD, was professor of technology management at the University of Massachusetts Amherst. Throughout his esteemed career, Dr. Bisgaard made significant research contributions in the areas of experimental design, operations management, time series analysis, and Lean Six Sigma. A Fellow of the American Statistical Association and the American Society for Quality, he was also one of the cofounders of the European Network for Business and Industrial Statistics (ESB1S) in 1999. Dr. Bisgaard was awarded many honors for his achievements in the field of statistics, including the Brumbaugh Award (1988, 1996, and 2008), the Shewhart Medal (2002), the William G. Hunter Award (2002), and the George Box Award (2004). Murat Kulahci, PHD, is Associate Professor of Statistics in the Department of Informatics and Mathematical Modeling at the Technical University of Denmark. He has authored or coauthored over forty journal articles in the areas of time series analysis, design of experiments, and statistical process control and monitoring. Dr. Kulahci is coauthor of Introduction to Time Series Analysis and Forecasting (Wiley).

Table of Contents

Preface	p. xi
Time Serirs Data: Examples and Basic Concepts	p. 1
Introduction	p. 1
Examples of Time Series Data	p. 1
Understanding Autocorrelation	p. 10
The Wold Decomposition	p. 12
The Impulse Response Function	p. 14
Superposition Principle	p. 15
Parsimonious Models	p. 18
Exercises	p. 19
Visualizing Time Series Data Structures: Graphical Tools	p. 21
Introduction	p. 21
Graphical Analysis of Time Series	p. 22
Graph Terminology	p. 23
Graphical Perception	p. 24
Principles of Graph Construction	p. 28
Aspect Ratio	p. 30
Time Series Plots	p. 34
Bad Graphics	p. 38
Exercises	p. 46
Stationary Models	p. 47
Basics of Stationary Time Series Models	p. 47
Autoregressive Moving Average (ARMA) Models	p. 54
Stationarity and Invertibility of ARMA Models	p. 62
Checking for Stationarity using Variogram	p. 66
Transformation of Data	p. 69
Exercises	p. 73
Nonstationary Models	p. 79
Introduction	p. 79
Detecting Nonstationarity	p. 79
Autoregressive Integrated Moving Average (ARIMA) Models	p. 83
Forecasting using ARIMA Models	p. 91
Example 2: Concentration Measurements from a Chemical Process	p. 93
The EWMA Forecast	p. 103
Exercises	p. 104
Seasonal Models	p. 111
Seasonal Data	p. 111
Seasonal Arima Models	p. 116
Forecasting using Seasonal Arima Models	p. 124
Example 2: Company X's Sales Data	p. 126
Exercises	p. 152
Time Series Model Selection	p. 155
Introduction	p. 155
Finding the "Best" Model	p. 155
Example: Internet Users Data	p. 156
Model Selection Criteria	p. 163
Impulse Response Function to Study the Differences in Models	p. 166
Comparing Impulse Response Functions for Competing Models	p. 169
Arima Models as Rational Approximations	p. 170
Ar Versus Arma Controversy	p. 171
Final Thoughts on Model Selection	p. 173
How to Compute Impulse Response Functionswith a Spreadsheet	p. 173
Exercises	p. 174
Additional Issues In Arima Models	p. 177
Introduction	p. 177
Linear Difference Equations	p. 177
Eventual Forecast Function	p. 183
Deterministic Trend Models	p. 187
Yet Another Argument for Differencing	p. 189
Constant Term in Arima Models	p. 190
Cancellation of Terms in Arima Models	p. 191
Stochastic Trend: Unit Root Nonstationary Processes	p. 194
Overdifferencing and Underdifferencing	p. 195
Missing Values in Time Series Data	p. 197
Exercises	p. 201
Transfer-Function Models	p. 203
Introduction	p. 203
Studying Input-Output Relationships	p. 203
Example 1: The Box-Jenkins' Gas Furnace	p. 204
Spurious Cross Correlations	p. 207
Prewhitening	p. 207
Identification of the Transfer Function	p. 213
Modeling the Noise	p. 215
The General Methodology for Transfer Function Models	p. 222
Forecasting Using Transfer Function-Noise Models	p. 224
Intervention Analysis	p. 238
Exercises	p. 261
Additional Topics	p. 263
Spurious Relationships	p. 263
Autocorrelation in Regression	p. 271
Process Regime Changes	p. 278
Analysis of Multiple Time Series	p. 296
Structural Analysis of Multiple Time Series	p. 296
Exercises	p. 310
Datasets Used in the Examples	p. 311
Temperature Readings from a Ceramic Furnace	p. 312
Chemical Process Temperature Readings	p. 313
Chemical Process Concentration Readings	p. 314
International Airline Passengers	p. 315
Company X's Sales Data	p. 316
Internet Users Data	p. 317
Historical Sea Level (mm) Data in Copenhagen, Denmark	p. 317
Gas Furnace Data	p. 318
Sales with Leading Indicator	p. 319
Crest/Colgate Market Share	p. 320
Simulated Process Data	p. 322
Coen et al. (1969) Data	p. 323
Temperature Data from a Ceramic Furnace	p. 324
Temperature Readings from an Industrial Process	p. 325
US Hog Series	p. 326
Datasets Used in the Exercise	p. 327
Beverage Amount (ml)	p. 328
Pressure of the Steam Fed to a Distillation Column (bar)	p. 329
Number of Paper Checks Processed in a Local Bank	p. 330
Monthly Sea Levels in Los Angeles, California (mm)	p. 331
Temperature Readings from a ChemicalTroeess (?C)	p. 334
Daily Average Exchange Rates between US Dollar and Euro	p. 335
Monthly US Unemployment Rates	p. 336
Monthly Residential Electricity Sales (MWh) and Average Residential Electricity Retail Price (c/kWh) in the United States	p. 337
Monthly Outstanding Consumer Credits Provided by Commercial Banks in the United States (million USD)	p. 340
100 Observations Simulated from an ARMA (1, 1) Process	p. 342
Quarterly Rental Vacancy Rates in the United States	p. 343
W?lfer Sunspot Numbers	p. 344
Viscosity Readings from a Chemical Process	p. 345
UK Midyear Population	p. 346
Unemployment and GDP data for the United Kingdom	p. 347
Monthly Crude Oil Production of OPEC Nations	p. 348
Quarterly Dollar Sales of Marshall Field & Company ($ 1000)	p. 360
Bibliography	p. 361
Index	p. 365
Table of Contents provided by Ingram. All Rights Reserved.