Griffith / Paelinck Non-standard Spatial Statistics and Spatial Econometrics

1. Auflage 2011
ISBN: 978-3-642-16043-1
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 264 Seiten

Reihe: Advances in Geographic Information Science

Despite spatial statistics and spatial econometrics both being recent sprouts of the general tree 'spatial analysis with measurement'-some may remember the debate after WWII about 'theory without measurement' versus 'measurement without theory'-several general themes have emerged in the pertaining literature. But exploring selected other fields of possible interest is tantalizing, and this is what the authors intend to report here, hoping that they will suscitate interest in the methodologies exposed and possible further applications of these methodologies. The authors hope that reactions about their publication will ensue, and they would be grateful to reader(s) motivated by some of the research efforts exposed hereafter letting them know about these experiences.

Autoren/Hrsg.

Griffith, Daniel A.

Paelinck, Jean H. Paul

Inhaltsverzeichnis

1;Preface;4
2;Prologue;5
3;Contents;28
4;Part I Non-standard Spatial Statistics;33
4.1;1 Introduction: Spatial Statistics;34
4.2;2 Individual Versus Ecological Analyses;35
4.2.1;2.1 Introduction;35
4.2.2;2.2 Spatial Autocorrelation Effects;35
4.2.3;2.3 Aggregation Impacts;36
4.2.3.1;2.3.1 The Syracuse Data;38
4.2.3.2;2.3.2 Previous Findings for Syracuse;40
4.2.4;2.4 Spatial Autocorrelation in the Syracuse Data;41
4.2.4.1;2.4.1 Spatial Autocorrelation in the Syracuse Data: LN(BLL + 1) Values;41
4.2.4.2;2.4.2 Spatial Autocorrelation in the Syracuse Data: Appraised House Value;43
4.2.5;2.5 Spatial Autocorrelation in the Syracuse Data: Other Sources;46
4.2.6;2.6 Bayesian Analysis Using Gibbs Sampling (BUGS) and Model Prediction Experiments;47
4.2.6.1;2.6.1 Results for the 2000 Census Tracts;50
4.2.7;2.7 Discussion and Implications;52
4.3;3 Statistical Models for Spatial Data: Some Linkages and Communalities;54
4.3.1;3.1 Introduction;54
4.3.2;3.2 Background: Quantifying Spatial Autocorrelation;55
4.3.2.1;3.2.1 The Moran Scatterplot;56
4.3.2.2;3.2.2 The Semivariogram Plot;57
4.3.3;3.3 Specifications of Spatial Autoregressive and Geostatistical Models;57
4.3.3.1;3.3.1 Spatial Autoregressive Models;58
4.3.4;3.4 Geostatistical Models;60
4.3.5;3.5 Linkages Between Spatial Autoregression and Geostatistics;61
4.3.6;3.6 A Major Commonality of Spatial Autoregression and Geostatistics;62
4.3.7;3.7 Implications for Quantitative Human Geography;64
4.4;4 Frequency Distributions for Simulated Spatially Autocorrelated Random Variables;65
4.4.1;4.1 Introduction;65
4.4.2;4.2 The Normal Probability Model;66
4.4.2.1;4.2.1 Simulating Spatially Autocorrelated Normal RVs;67
4.4.2.2;4.2.2 Simulation Results for an Ideal Regular Hexagonal Surface Partitioning;69
4.4.2.3;4.2.3 Simulation Results for the China County Geographic Configuration;73
4.4.2.4;4.2.4 Implications;76
4.4.3;4.3 The Poisson Probability Model;78
4.4.3.1;4.3.1 Simulating Spatially Autocorrelated Poisson RVs;80
4.4.3.1.1;4.3.1.1 MCMC Map Simulation;81
4.4.3.1.2;4.3.1.2 SF Map Simulation;83
4.4.3.2;4.3.2 Simulation Results for an Ideal Regular Hexagonal Surface Partitioning;83
4.4.3.3;4.3.3 Simulation Results for the China County Geographic Configuration;84
4.4.3.4;4.3.4 Implications;88
4.4.4;4.4 The Binomial Probability Model, N > 1;90
4.4.4.1;4.4.1 Simulating Spatially Autocorrelated Binomial RVs;91
4.4.4.2;4.4.2 Simulation Results for an Ideal Regular Hexagonal Surface Partitioning;93
4.4.4.3;4.4.3 Simulation Results for the China County Geographic Configuration;96
4.4.4.4;4.4.4 Implications;98
4.4.5;4.5 Discussion;99
4.5;5 Understanding Correlations Among Spatial Processes;102
4.5.1;5.1 Introduction;102
4.5.2;5.2 Two Illustrative Examples;102
4.5.3;5.3 Geostatistical Semivariogram Model Implications;104
4.5.4;5.4 Spatial Autoregressive Model Implications;109
4.5.4.1;5.4.1 Variance and Covariance Inflation Attributable to Spatial Autocorrelation;112
4.5.4.2;5.4.2 Effective Sample Size as a Function of .X and .Y;114
4.5.5;5.5 Spatial Filtering Model Implications;116
4.5.5.1;5.5.1 Correlation Coefficient Decomposition;117
4.5.5.2;5.5.2 Variance Inflation;120
4.5.6;5.6 Discussion;120
4.6;6 Spatially Structured Random Effects: A Comparison of Three Popular Specifications;123
4.6.1;6.1 Introduction;123
4.6.2;6.2 Modeling Spatial Structure;123
4.6.3;6.3 Linear Mixed Models;125
4.6.4;6.4 Generalized Linear Mixed Models;131
4.6.5;6.5 Degrees of Freedom for GLMM Random Effects;136
4.6.6;6.6 Extensions to Space-Time Data Sets;137
4.6.7;6.7 Discussion and Implications;140
4.7;7 Spatial Filter Versus Conventional Spatial Model Specifications: Some Comparisons;142
4.7.1;7.1 Introduction;142
4.7.1.1;7.1.1 Background;142
4.7.2;7.2 Variation and Covariation Considerations for Poisson Random Variables;145
4.7.2.1;7.2.1 Heterogeneity in Counts Data;146
4.7.2.2;7.2.2 Spatial Autocorrelation in Poisson Random Variables;149
4.7.2.3;7.2.3 Spatial Autocorrelation-induced Correlation Inflation;151
4.7.3;7.3 Principal Spatial Statistical Model Specifications;155
4.7.3.1;7.3.1 The Log-normal Approximation;155
4.7.3.2;7.3.2 A Winsorized Auto-Poisson Model;156
4.7.3.3;7.3.3 A Proper CAR Model Specification via GeoBUGS;159
4.7.4;7.4 Spatial Filter Model Specifications;161
4.7.4.1;7.4.1 The Log-normal Approximation Spatial Filter Model;161
4.7.4.2;7.4.2 A Poisson Spatial Filter Model;162
4.7.4.3;7.4.3 A Spatial Filter Model Specification via BUGS;164
4.7.5;7.5 Discussion;165
4.7.5.1;7.5.1 Cross-validation Results for the Poisson Spatial Filter Model;166
4.7.5.2;7.5.2 A Simulation Experiment Based Upon the Poisson Spatial Filter Model;166
4.7.5.3;7.5.3 Impacts of Incorporating Additional Information;168
4.7.5.4;7.5.4 Implications for Data Mapping;169
4.7.6;7.6 Concluding Comments;172
4.8;8 The Role of Spatial Autocorrelation in Prioritizing Sites Within a Geographic Landscape;175
4.8.1;8.1 Introduction: The Problem;175
4.8.2;8.2 The Murray Superfund Site: Part I;176
4.8.2.1;8.2.1 State-of-the-Art Practice;177
4.8.2.2;8.2.2 A Spatial Methodology: Stage 1, Spatial Sampling Data Collection and Preprocessing;178
4.8.3;8.3 The Murray Superfund Site: Part II;180
4.8.3.1;8.3.1 A Spatial Methodology: Stage 2, Spatial Statistics for Calculating UCLs;183
4.8.4;8.4 The Murray Superfund Site: Part III;185
4.8.4.1;8.4.1 A Spatial Methodology: Stage 3, Prioritizing Subregions for Remediation;187
4.8.5;8.5 The Murray Superfund Site: Part IV;187
4.8.5.1;8.5.1 A Spatial Methodology: Stage 4, Covariation of Contaminants and Joint Pollutant Analyses;188
4.8.6;8.6 The Murray Superfund Site: Part V;192
4.8.7;8.7 Implications;194
4.9;9 General Conclusions: Spatial Statistics;195
5;Part II Non-standard Spatial Econometrics;198
5.1;10 Introduction: Spatial Econometrics;199
5.2;11 A Mixed Linear-Logarithmic Specification forINTnl; Lotka-Volterra Models with Endogenously Generated SDLS-Variables;200
5.2.1;11.1 Lotka-Volterra Models;200
5.2.1.1;11.1.1 A General Specification;200
5.2.1.2;11.1.2 Applications;201
5.2.1.3;11.1.3 Simultaneous Dynamic Least Squares (SDLS) Estimation;202
5.2.2;11.2 Mixed Specification;203
5.2.2.1;11.2.1 Equations;203
5.2.2.2;11.2.2 Stability;204
5.2.3;11.3 Application;204
5.2.4;11.4 Conclusion;207
5.3;12 Selecting Spatial Regimes by Threshold Analysis;209
5.3.1;12.1 Method;209
5.3.2;12.2 Spatial Income Generating Model;210
5.3.3;12.3 A Spatial Activity Complex Model;213
5.3.4;12.4 Conclusion;217
5.3.5;12.5 Appendix;217
5.4;13 Finite Automata;218
5.4.1;13.1 A Finite Automaton Bi-regional Dynamic Model;218
5.4.2;13.2 An Empirical Application;222
5.4.3;13.3 Conclusion;224
5.5;14 Learning from Residuals;226
5.5.1;14.1 Residuals;226
5.5.2;14.2 Multiple Regimes;228
5.5.3;14.3 Spatial Interpolation;231
5.5.4;14.4 Composite Parameters;232
5.5.5;14.5 Conclusion;234
5.6;15 Verhulst and Poisson Distributions;235
5.6.1;15.1 Robust Estimation in the Binary Case: A Linear Logistic Estimator (LLE);235
5.6.2;15.2 A Logistic Dynamic Share Model;237
5.6.3;15.3 A Linear Poisson Distribution Estimator;239
5.6.4;15.4 Conclusion;243
5.7;16 Qualireg, A Qualitative Regression Method;244
5.7.1;16.1 Qualiflex;244
5.7.2;16.2 Qualireg;247
5.7.3;16.3 Spatial Setting;248
5.7.4;16.4 Conclusion;250
5.8;17 Filtering Complexity for Observational Errors and Spatial Bias;251
5.8.1;17.1 Complexity, Estimation and Testing;251
5.8.2;17.2 Filtering for Observational Errors;253
5.8.3;17.3 Further Filtering for Spatial Bias;256
5.8.4;17.4 Conclusions;257
5.9;18 General Spatial Econometric Conclusions;259
5.10;Epilogue;260
5.11;References;262
5.12;Author Index;272
5.13;Subject Index;273