Practical Business Forecasting

by Evans, Michael K.

• ISBN13: 9780631220664
• ISBN10: 0631220666
• Edition: 1st
• Format: Paperback
• Copyright: 2009-08-03
• Publisher: Wiley-Blackwell

Summary

Stressing the concrete applications of economic forecasting, Practical Business Forecasting is accessible to a wide-range of readers, requiring only a familiarity with basic statistics. The text focuses on the use of models in forecasting, explaining how to build practical forecasting models that produce optimal results. In a clear and detailed format, the text covers estimating and forecasting with single and multi- equation models, univariate time-series modeling, and determining forecasting accuracy. Additionally, case studies throughout the book illustrate how the models are actually estimated and adjusted to generate accurate forecasts. After reading this text, students and readers should have a clearer idea of the reasoning and choices involved in building models, and a deeper foundation in estimating econometric models used in practical business forecasting.

Author Biography

Dr. Michael K. Evans formerly taught at the Kellogg School at Northwestern University. Since 1981 has headed Evans, Carroll & Associates (formerly Evans Economics), and has generated thousands of forecasts at the macroeconomic, financial, industry, and individual company level. He was awarded the Annual Blue Chip Economic Forecasting Award in 1999 for the most accurate macroeconomic forecasts over the past four years

Table of Contents

Choosing the Right Type of Forecasting Model:

Introduction

Statistics, Econometrics, and Forecasting

Concept of Forecast Accuracy: Compared to What?

Structural Shifts in Parameters

Model Misspecification

Missing, Smoothed, Preliminary, or Inaccurate Data

Changing Expectations by Economic Agents

Policy Shifts

Unexpected Changes in Exogenous Variables

Incorrect Assumptions about Exogenity

Error Buildup in Multi-Period Forecasts

Alternative Types of Forecasts:

Point or Interval

Absolute or Conditional

Alternative Scenarios Weighed by Probabilities

Asymmetric

Single or Multi Period

Short Run or Long Range

Forecasting Single or Multiple Variables

Some Common Pitfalls in Building Forecasting Equations:

Useful Tools for Practical Business Forecasting:

Introduction

Types and Sources of Data:

Time Series, Cross Section, and Panel Data

Basic Sources of U.S. Government Data

Major Sources of International Government Data

Principal Sources of Key Private Sector Data

Collecting Data from the Internet:

Forecasting Under Uncertainty

Utilizing Graphs and Charts

Mean and Variance

Goodness of Fit Statistics:

Covariance and Correlation Coefficients

Standard Errors and t-ratios

F-ratios and Adjusted R-squared

Using the EViews Statistical Package

Utilizing Graphs and Charts

Checklist Before Analyzing Data

Adjusting for Seasonal Factors

Checking for Outlying Values

Using Logarithms and Elasticities

The General Linear Regression Model:

Introduction

The General Linear Model:

The Bivariate Case

Desirable Properties of Estimators

Expanding to the Multivariate Case

Uses and Misuses of R-Bar Squared:

Differences Between R-Square and R-Bar Square

Pitfalls in Trying to Maximize R-Bar Square

An Example: the Simple Consumption Function

Measuring And Understanding Partial Correlation:

Covariance and the Correlation Matrix

Partial Correlation Coefficients

Pitfalls Of Stepwise Regression

Testing and Adjusting for Autocorrelation:

Why Autocorrelation Occurs and What it Means

Durbin-Watson Statistic to Measure Autocorrelation

Autocorrelation Adjustments: Cochrane-Orcutt and Hildreth-Lu

Higher Order Autocorrelation

Overstatement of t-ratios When Autocorrelation is Present

Pitfalls of Using the Lagged Dependent Variable

Testing and Adjusting for Heteroscedasticity:

Causes of Heteroscedasticity in Cross-Section and Time-Series Data

Measuring and Testing for Heteroscedasticity

Getting Started: An Example in Eviews:

Case Study #1: Predicting Retail Sales for Hardware Stores

Case Study #2: German Short-Term Interest Rates

Case Study #3: Lumber Prices

Additional Topics for Single-Equation Regression Models:

Introduction

Problems Caused by Multicollinearity

Eliminating or Reducing Spurious Trends:

Case Study #4. Demand for Airline Travel

Log-Linear Transformation

Percentage First Differences

Ratios

Deviations Around Trends

Weighted Least Squares

Summary and Comparison of Methods

Distributed Lags:

General Discussion of Distributed Lags

Polynomial Distributed Lags

General Guidelines for Using PDLs

Treatment of Outliers and Issues of Data Adequacy

Outliers

Missing Observations

General Comments of Data Adequacy

Uses and Misuses of Dummy Variables:

Single-Event Dummy Variables

Changes in Dummy Variables for Institutional Structure

Changes in Slope Coefficients

Nonlinear Regressions:

Log-Linear Regressions

Quadratic and Other Powers, Including Inverse

Ceilings, Floors, and Kronecker Deltas: Linearizing with Dummy Variables

General Steps For Formulating A Multiple Regression Equation

Case Study #5: The Consumption Function

Case Study #6: Capital Spending

Forecasting with a Single-Equation Regression Model:

Introduction

Checking for Normally Distributed Residuals:

Higher Order Tests for Autocorrelation

Tests For Heteroscedasticity

Testing for Equation Stability and Robustness:

Chow Test for Equation Stability

Ramsey RESET Test to Detect Misspecification

Recursive Least Squares – Testing Outside The Sample Period

Additional Comments on Multicollinearity

Case Study #7: Demand for Motor Vehicles

Evaluating Forecast Accuracy

The Effect of Forecasting Errors in the Independent Variables

Case Study #8: Housing Starts

Comparison with Naïve Models:

Same Level or Percentage Change

Naïve Models Using Lagged Values of the Dependent Variables

Adjusting the Coefficients of the Model When Forecasting

Buildup of Forecast Error Outside the Sample Period:

Increased Distance from the Mean Value

Unknown Values of Independent Variables

Error Buildup in Multi Period Forecasting

Case Study #9: The Yen/Dollar Crossrate

Elements Of Univariate Time-Series Methods:

Introduction

The Basic Time-Series Decomposition Model

Case Study #10. General Merchandise Sales

Identifying the Trend

Measuring the Seasonal Factor

Separating Cyclical and Irregular Components

Linear and Nonlinear Trends

Methods of Smoothing Data:

Arithmetic Moving Averages

Exponential Smoothing

Holt-Winters Method

Hodrick-Prescott Filter

Methods of Seasonal Adjustment:

Arithmetic and Multiplicative Fixed Weights

Variable Weights

Treatment of Outlying Observations

Seasonal Adjustment Factors with the Census Bureau X-11 Program

Case Study #11 : Manufacturing Inventory Stocks for Textile Mill Products

Case Study #12: Seasonally Adjusted Gasoline Prices

Univariate Time Series Modeling and Forecasting:

Introduction

Box-Jenkins Philosophy: Combining Theoretical and Practical Forecasts

ARIMA Models:

First-Order Autoregressive Models – AR(1)

AR(2) Models

AR(N) Models

Moving Average Models

ARMA Procedures

Stationary and Integrated Series

Identification

Seasonal Factors in ARMA Modeling

Estimation of ARMA Models

Diagnostic Checking and Forecasting

Case Study #13: New Orders for Machine Tools

Case Study #14: Inventory/Sales (I/S) Ratio for SIC 37 (Transportation Equipment)

Case Study #15: Nonfarm Payroll Employment

Combining Forecasts:

Introduction

Outline of the Theory of Forecast Combination

Major Sources of Forecast Error

Combining Methods of Nonstructural Estimation

Combining Structural and Nonstructural Methods

Case Study #16: Purchases of Consumer Durables

The Role of Judgment in Forecasting:

Surveys of Sentiment and Buying Plans

Sentiment Index for Prospective Home Buyers

The Role of Consensus Forecasts

Case Study #17: Predicting Interest Rates by Combining Structural and Consensus Forecasts

Adjusting Constant Terms and Slope Coefficients:

Advantages and Pitfalls of Adjusting the Constant Term

Estimating Shifting Parameters

Combining Forecasts: Summary

Case Study #18: Improving the Forecasting Record for Inflation

Building and Presenting Short-Term Sales Forecasting Models:

Introduction

Organizing the Sales Forecasting Procedure

Endogenous and Exogenous Variables in Sales Forecasting:

Macroeconomic Variables

Variables Controlled by the Firm

Variables Reflecting Competitive Response

The Role of Judgment:

Deflecting Excess Optimism

The Importance of Accurate Macroeconomic Forecasts

Assessing Judgmental Inputs

Presenting Sales Forecasts:

Purchases of Construction Equipment

Retail Furniture Sales

Case Study #19: The Demand for Bicycles

Case Study #20: New Orders for Machine Tools

Case Study #21: Purchases of Farm Equipment

Methods of Long-Term Forecasting:

Introduction

Nonparametric Methods of Long-Term Forecasting:

Survey Methods

Analogy and Precursor Methods

Scenario Analysis

Delphi Analysis

Statistical Methods of Determining Nonlinear Trends: Nonlinear Growth and Decline, Logistics, and Saturation Curves:

Nonlinear Growth and Decline Curves

Logistics Curves (S-Curves)

Saturation Curves

Case Study #22: Growth in E-Commerce

Predicting Trends Where Cyclical Influences are Important

Case Study #23: Sales of Personal Computers

Projecting Long-Run Trends in Real Growth

Case Study #24: Projecting Long-Term Growth Rates in Japan and Korea

Forecasting Very Long-Range Trends: Population and Natural Resource Trends:

Predicting Long-Term Trends in Population Growth

Predicting Long-Term Trends in Natural Resource Prices

Simultaneous Equation Models:

Introduction

Simultaneity Bias in a Single Equation

Estimating Simultaneous Equation Models

Case Study #25; Submodel for Prices and Wages

Further Issues in Simultaneous Equation Model Forecasting

Case Study #26: Simultaneous Determination of Inflation, Short-Term and Long-Term Interest Rates, and Stock Prices

Case Study #27: Simultaneous Determination of Industrial Production, Producers Durable Equipment, Inventory Investment, and Imports

Summary

Alternative Methods of Macroeconomic Forecasting:

Introduction

Structural vs VAR Models

Solving Structural Macroeconomic Models:

Outlining the Equilibrium Structure

Newton-Raphson Method and the Gauss-Seidel Algorithm

The Triangular Structure

A Prototype Macroeconomic Model:

Summary of Macroeconomic Model Equations

Treatment of Trends and Autocorrelation

Simulating the Model

Preparing the Model for Forecasting:

Forecasting With AR(1) Adjustments

Forecasting With Constant Adjustments

Comparison of Alternative Forecasts

Using the Leading Indicators for Macroeconomic Forecasting

Using Indexes of Consumer and Business Sentiment for Forecasting

Table of Contents provided by Publisher. All Rights Reserved.