Spatial Econometrics using Microdata

This book provides an introduction to spatial analyses concerning disaggregated (or micro) spatial data.

Particular emphasis is put on spatial data compilation and the structuring of the connections between the observations. Descriptive analysis methods of spatial data are presented in order to identify and measure the spatial, global and local dependency.

The authors then focus on autoregressive spatial models, to control the problem of spatial dependency between the residues of a basic linear statistical model, thereby contravening one of the basic hypotheses of the ordinary least squares approach.

This book is a popularized reference for students looking to work with spatialized data, but who do not have the advanced statistical theoretical basics.

ACKNOWLEDGMENTS  ix

PREFACE   xi

CHAPTER 1. ECONOMETRICS AND SPATIAL DIMENSIONS 1

1.1. Introduction   1

1.2. The types of data  6

1.2.1. Cross-sectional data    7

1.2.2. Time series 8

1.2.3. Spatio-temporal data    9

1.3. Spatial econometrics   11

1.3.1. A picture is worth a thousand words 13

1.3.2. The structure of the databases of spatial microdata 15

1.4. History of spatial econometrics    16

1.5. Conclusion   21

CHAPTER 2. STRUCTURING SPATIAL RELATIONS   29

2.1. Introduction   29

2.2. The spatial representation of data    30

2.3. The distance matrix   34

2.4. Spatial weights matrices    37

2.4.1. Connectivity relations  40

2.4.2. Relations of inverse distance    42

2.4.3. Relations based on the inverse (or negative) exponential 45

2.4.4. Relations based on Gaussian transformation 47

2.4.5. The other spatial relation   47

2.4.6. One choice in particular?   48

2.4.7. To start   49

2.5. Standardization of the spatial weights matrix   50

2.6. Some examples 51

2.7. Advantages/disadvantages of micro-data 55

2.8. Conclusion   56

CHAPTER 3. SPATIAL AUTOCORRELATION 59

3.1. Introduction   59

3.2. Statistics of global spatial autocorrelation  65

3.2.1. Moran’s I statistic    68

3.2.2. Another way of testing significance 72

3.2.3. Advantages of Moran’s I statistic in modeling   74

3.2.4. Moran’s I for determining the optimal form of W    75

3.3. Local spatial autocorrelation   77

3.3.1. The LISA indices   79

3.4. Some numerical examples of the detection tests   86

3.5. Conclusion   89

CHAPTER 4. SPATIAL ECONOMETRIC MODELS   93

4.1. Introduction   93

4.2. Linear regression models  95

4.2.1. The different multiple linear regression model types  99

4.3. Link between spatial and temporal models  102

4.3.1. Temporal autoregressive models   103

4.3.2. Spatial autoregressive models    110

4.4. Spatial autocorrelation sources    115

4.4.1. Spatial externalities    117

4.4.2. Spillover effect     119

4.4.3. Omission of variables or spatial heterogeneity  123

4.4.4. Mixed effects  127

4.5. Statistical tests 129

4.5.1. LM tests in spatial econometrics   134

4.6. Conclusion   140

CHAPTER 5. SPATIO-TEMPORAL MODELING  145

5.1. Introduction   145

5.2. The impact of the two dimensions on the structure of the links: structuring of spatio-temporal links  148

5.3. Spatial representation of spatio-temporal data   150

5.4. Graphic representation of the spatial data generating processes pooled over time   154

5.5. Impacts on the shape of the weights matrix  159

5.6. The structuring of temporal links: a temporal weights matrix    162

5.7. Creation of spatio-temporal weights matrices   167

5.8. Applications of autocorrelation tests and of autoregressive models    170

5.9. Some spatio-temporal applications  172

5.10. Conclusion   173

CONCLUSION    177

GLOSSARY   185

APPENDIX   189

BIBLIOGRAPHY  215

INDEX    227

Jean DUBÉ is Professor in regional development at Laval University, Canada.

Diègo LEGROS is a lecturer in economics and management at the University of Burgundy, France.