Business Forecasting with ForecastX

Title
Contents
1 Introduction to Business Forecasting
	Introduction
		Comments from the Field
	Quantitative Forecasting Has Become Widely Accepted
	Forecasting in Business Today
		Krispy Kreme
		Bell Atlantic
		Columbia Gas
		Segix Italia
		Pharmaceuticals in Singapore
		Fiat Auto
		Brake Parts, Inc.
		Some Global Forecasting Issues: Examples from Ocean Spray Cranberries
	Forecasting in the Public and Not-for-Profit Sectors
	Forecasting and Supply Chain Management
	Collaborative Forecasting
	Computer Use and Quantitative Forecasting
	Qualitative or Subjective Forecasting Methods
		Sales Force Composites
		Surveys of Customers and the General Population
		Jury of Executive Opinion
		The Delphi Method
		Some Advantages and Disadvantages of Subjective Methods
	New-Product Forecasting
		Using Marketing Research to Aid New-Product Forecasting
		The Product Life Cycle Concept Aids in New-Product Forecasting
		Analog Forecasts
			New Product and Penetration Curves for VCR Sales
		Test Marketing
		Product Clinics
		Type of Product Affects New-Product Forecasting
		The Bass Model for New-Product Forecasting
		Forecasting Sales for New Products That Have Short Product Life Cycles
	Two Simple Naive Models
	Evaluating Forecasts
	Using Multiple Forecasts
	Sources of Data
	Forecasting Total Houses Sold
	Overview of the Text
		Comments from the Field
	Integrative Case: Forecasting Sales of The Gap
		Comments from the Field
	John Galt Partial Customer List
	An Introduction to ForecastX 7.0
		Forecasting with the ForecastX Wizard™
		Using the Five Main Tabs on the Opening ForecastX Screen
	Suggested Readings and Web Sites
	Exercises
2 The Forecast Process, Data Considerations, and Model Selection
	Introduction
	The Forecast Process
	Trend, Seasonal, and Cyclical Data Patterns
	Data Patterns and Model Selection
	A Statistical Review
		Descriptive Statistics
		The Normal Distribution
		The Student’s t-Distribution
		From Sample to Population: Statistical Inference
		Hypothesis Testing
		Correlation
	Correlograms: Another Method of Data Exploration
	Total Houses Sold: Exploratory Data Analysis and Model Selection
		Business Forecasting: A Process, Not an Application
	Integrative Case: The Gap
		Comments from the Field
	Using ForecastX™ to Find Autocorrelation Functions
	Suggested Readings
	Exercises
3 Moving Averages and Exponential Smoothing
	Moving Averages
	Simple Exponential Smoothing
	Holt’s Exponential Smoothing
	Winters’ Exponential Smoothing
		The Seasonal Indices
	Adaptive–Response-Rate Single Exponential Smoothing
	Using Single, Holt’s, or ADRES Smoothing to Forecast a Seasonal Data Series
	New-Product Forecasting (Growth Curve Fitting)
		Gompertz Curve
		Logistics Curve
		Bass Model
			The Bass Model in Action
	Event Modeling
	Forecasting Jewelry Sales and Houses Sold with Exponential Smoothing
		Jewelry Sales
		Houses Sold
	Summary
	Integrative Case: The Gap
	Using ForecastX™ to Make Exponential Smoothing Forecasts
	Suggested Readings
	Exercises
4 Introduction to Forecasting with Regression Methods
	The Bivariate Regression Model
	Visualization of Data: An Important Step in Regression Analysis
	A Process for Regression Forecasting
	Forecasting with a Simple Linear Trend
	Using a Causal Regression Model to Forecast
	A Jewelry Sales Forecast Based on Disposable Personal Income
	Statistical Evaluation of Regression Models
		Basic Diagnostic Checks for Evaluating Regression Results
	Using the Standard Error of the Estimate
	Serial Correlation
	Heteroscedasticity
	Cross-Sectional Forecasting
	Forecasting Total Houses Sold with Two Bivariate Regression Models
		Comments from the Field
	Integrative Case: The Gap
		Comments from the Field
	Using ForecastX™ to Make Regression Forecasts
	Further Comments on Regression Models
	Suggested Readings
	Exercises
5 Forecasting with Multiple Regression
	The Multiple-Regression Model
	Selecting Independent Variables
	Forecasting with a Multiple-Regression Model
		The Regression Plane
	Statistical Evaluation of Multiple-Regression Models
		Three Quick Checks in Evaluating Multiple- Regression Models
		Multicollinearity
			The Demand for Nurses
		Serial Correlation: A Second Look
	Serial Correlation and the Omitted-Variable Problem
		Alternative-Variable Selection Criteria
	Accounting for Seasonality in a Multiple-Regression Model
	Extensions of the Multiple-Regression Model
	Advice on Using Multiple Regression in Forecasting
	Forecasting Jewelry Sales with Multiple Regression
		Forecasting Consumer Products
	Integrative Case: The Gap
	Using ForecastX™ to Make Multiple-Regression Forecasts
	Suggested Readings
	Exercises
6 Time-Series Decomposition
	The Basic Time-Series Decomposition Model
	Deseasonalizing the Data and Finding Seasonal Indices
	Finding the Long-Term Trend
	Measuring the Cyclical Component
		Overview of Business Cycles
		Business Cycle Indicators
		The Cycle Factor for Private Housing Starts
	The Time-Series Decomposition Forecast
		Forecasting Shoe Store Sales by Using Time-Series Decomposition
		Forecasting Total Houses Sold by Using Time-Series Decomposition
			Forecasting Winter Daily Natural Gas Demand at Vermont Gas Systems
	Integrative Case: The Gap
	Using ForecastX™ to Make Time-Series Decomposition Forecasts
	Suggested Readings
	Exercises
	Appendix: Components of the Composite Indices
7 ARIMA (Box-Jenkins)–Type Forecasting Models
	Introduction
	The Philosophy of Box-Jenkins
	Moving-Average Models
	Autoregressive Models
	Mixed Autoregressive and Moving-Average Models
	Stationarity
	The Box-Jenkins Identification Process
		Comments from the Field: An Overview of INTELSAT Forecasting
	ARIMA: A Set of Numerical Examples
		Example 1
		Example 2
		Example 3
		Example 4
	Forecasting Seasonal Time Series
	Total Houses Sold
		Intelligent Transportation Systems
	Integrative Case: Forecasting Sales of The Gap
	Using ForecastX™ to Make ARIMA (Box-Jenkins) Forecasts
	Suggested Readings
	Exercises
	Appendix: Critical Values of Chi-Square
8 Combining Forecast Results
	Introduction
	Bias
	An Example
	What Kinds of Forecasts Can Be Combined?
	Considerations in Choosing the Weights for Combined Forecasts
	Three Techniques for Selecting Weights When Combining Forecasts
		Justice Is Forecast
		An Application of the Regression Method for Combining Forecasts
	Forecasting Total Houses Sold with a Combined Forecast
		Comments from the Field: Combining Forecasts Can Improve Results
	Integrative Case: Forecasting The Gap Sales Data with a Combination Model
	Using ForecastX™ to Combine Forecasts
	Suggested Readings
	Exercises
9 Data Mining
	Introduction
	Data Mining
		Comments from the Field
	The Tools of Data Mining
		Business Forecasting and Data Mining
	A Data Mining Example: k-Nearest-Neighbor
		Comments from the Field: Cognos
	A Business Data Mining Example: k-Nearest-Neighbor
	Classification Trees: A Second Classification Technique
		A Business Data Mining Example: Classification Trees
	Naive Bayes: A Third Classification Technique
		Comments from the Field
	Regression: A Fourth Classification Technique
		Comments from the Field: Fool’s Gold
	Summary
	Suggested Readings
	Exercises
10 Forecast Implementation
	Keys to Obtaining Better Forecasts
	The Forecast Process
		Step 1. Specify Objectives
		Step 2. Determine What to Forecast
		Step 3. Identify Time Dimensions
		Step 4. Data Considerations
			How to Evaluate and Improve a Forecasting Process
		Step 5. Model Selection
		Step 6. Model Evaluation
		Step 7. Forecast Preparation
		Step 8. Forecast Presentation
		Step 9. Tracking Results
	Choosing the Right Forecasting Techniques
		Sales Force Composite (SFC)
		Customer Surveys (CS)
		Jury of Executive Opinion (JEO)
		Delphi Method
		Naive
		Moving Averages
		Simple Exponential Smoothing (SES)
		Adaptive–Response-Rate Single Exponential Smoothing (ADRES)
		Holt’s Exponential Smoothing (HES)
		Winters’ Exponential Smoothing (WES)
		Regression-Based Trend Models
		Regression-Based Trend Models with Seasonality
			Comments from the Field
		Regression Models with Causality
			Comments from the Field
		Time-Series Decomposition (TSD)
		ARIMA
	Special Forecasting Considerations
		Event Modeling
		Combining Forecasts
		New-Product Forecasting (NPF)
		Data Mining
			Comments from the Field
	Summary
	Using ProCast™ in ForecastX™ to Make Forecasts
	Suggested Readings
	Exercises
Index