- Preface, ii
- Chapter 1. Introduction, Background, and Caveats, 1
- 1.1. The MINITAB commercial software package, 1
- 1.2. The Moran Coefficient and the Geary Ratio, 3
- 1.3. Types of autoregressive models
- 1.4. Statistical Properties of OLS versus SAR, 7
- 1.5. What the SAR model estimation procedure accomplishes
- Chapter 2. OLS Regression with a Test for Spatial Autocorrelation
- 2.1. The Moran Coefficient for Regression Residuals, 10
- 2.2. Benchmark output for the Eire data, 15
- 2.3. Illustrative output for the Puerto Rican data, 18
- Appendix 2-A. Eire Data from Cliff and Ord, 22
- Appendix 2-B. Illustrative Puerto Rican Data: Production Density for the Mayaguez Agricultural Administrative Region, 23
- Chapter 3. Statistical Techniques that are Executable as an OLS Regression, 24
- 3.1. Inference about the population mean, 24
- 3.2. One-way Analysis of Variance (ANOVA), 30
- 3.3. Two-groups discriminant function analysis, 34
- 3.4. Bivariate correlation, 38
- 3.5. Trend surface models: linear, quadratic, and cubic forms, 42
- Chapter 4. Estimating an SAR Error Model, 49
- 4.1. The estimation algorithm, 50
- 4.2. Illustrative estimations for problems from Chapter 3, 53
- 4.3. Benchmark output for the California plant species data, 58
- Appendix 4-A. California Data from Upton and Fingleton, 63
- Chapter 5. Comparison of OLS and SAR Results: Evaluating the SAR Solution, 65
- 5.1. The estimation algorithm, 66
- 5.2. Illustrative evaluations for selected problems from Chapter 4, 70
- 5.3. Benchmark output for the California plant species data, 73
- Chapter 6. Summary, 77
- Chapter 7. References, 80
Appendix A. MSE Plots Versus Spatial Autocorrelation Estimates, 81