Spatial Microeconometrics

Description

Cover Half Title Series Page Title Page Copyright Page Dedication Table of Contents Foreword Preface and acknowledgements PART I: Introduction 1 Foundations of spatial microeconometrics modeling 1.1 A micro-level approach to spatial econometrics 1.2 Advantages of spatial microeconometric analysis 1.3 Sources of spatial micro-data 1.4 Sources of uncertainty in spatial micro-data 1.5 Conclusions and plan of the book PART II: Modeling the spatial behavior of economic agents in a given set of locations 2 Preliminary definitions and concepts 2.1 Neighborhood and the W matrix 2.2 Moran’s I and other spatial correlation measures 2.3 The Moran scatterplot and local indicators of spatial correlation 2.4 Conclusions 3 Basic cross-sectional spatial linear models 3.1 Introduction 3.2 Regression models with spatial autoregressive components 3.2.1 Pure spatial autoregression 3.2.2 The spatial error model 3.2.3 The spatial lag model 3.2.4 The spatial Durbin model 3.2.5 The general spatial autoregressive model with spatial autoregressive error structure 3.3 Test of residual spatial autocorrelation with explicit alternative hypotheses 3.4 Marginal impacts 3.5 Effects of spatial imperfections of micro-data 3.5.1 Introduction 3.5.2 Measurement error in spatial error models 3.5.3 Measurement error in spatial lag models 3.6 Problems in regressions on a spatial distance 4 Non-linear spatial models 4.1 Non-linear spatial regressions 4.2 Standard non-linear models 4.2.1 Logit and probit models 4.2.2 The tobit model 4.3 Spatial probit and logit models 4.3.1 Model specification 4.3.2 Estimation 4.4 The spatial tobit model 4.4.1 Model specification 4.4.2 Estimation 4.5 Further non-linear spatial models 4.6 Marginal impacts in spatial non-linear models 5 Space–time models 5.1 Generalities 5.2 Fixed and random effects models 5.3 Random effects spatial models 5.4 Fixed effect spatial models 5.5 Estimation 5.5.1 Introduction 5.5.2 Maximum likelihood 5.5.2.1 Likelihood procedures for random effect models 5.5.2.2 Likelihood procedures for fixed effect models 5.5.3 The generalized method of moments approach 5.5.3.1 Generalized method of moments procedures for random effects models 5.5.3.2 Generalized method of moments procedures for fixed effects models 5.6 A glance at further approaches in spatial panel data modeling PART III: Modeling the spatial locational choices of economic agents 6 Preliminary definitions and concepts in point pattern analysis 6.1 Spatial point patterns of economic agents 6.2 The hypothesis of complete spatial randomness 6.3 Spatial point processes 6.3.1 Homogeneous Poisson point process 6.3.2 Aggregated point processes 6.3.2.1 Inhomogeneous Poisson point processes 6.3.2.2 Cox processes 6.3.2.3 Poisson cluster point processes 6.3.3 Regular point processes 6.4 Classic exploratory tools and summary statistics for spatial point patterns 6.4.1 Quadrat-based methods 6.4.2 Distance-based methods 7 Models of the spatial location of individuals 7.1 Ripley’s K-function 7.2 Estimation of Ripley’s K-function 7.3 Identification of spatial location patterns 7.3.1 The CSR test 7.3.2 Parameter estimation of the Thomas cluster process 7.3.3 Parameter estimation of the Matérn cluster process 7.3.4 Parameter estimation of the log-Gaussian Cox process 8 Points in a heterogeneous space 8.1 Diggle and Chetwynd’s D-function 8.2 Baddeley, Møller and Waagepetersen’s K[sub(inhom)] -function 8.2.1 Estimation of K[sub(inhom)]-function 8.2.2 Inference for K[sub(inhom)] -function 8.3 Measuring spatial concentration of industries: Duranton–Overman K-density and Marcon–Puech M-function 8.3.1 Duranton and Overman’s K-density 8.3.2 Marcon and Puech’s M-function 9 Space–time models 9.1 Diggle, Chetwynd, Häggkvist and Morris’ space–time K-function 9.1.1 Estimation of space–time K-function 9.1.2 Detecting space–time clustering of economic events 9.2 Gabriel and Diggle’s STIK-function 9.2.1 Estimation of STIK-function and inference PART IV: Looking ahead: modeling both the spatial location choices and the spatial behavior of economic agents 10 Firm demography and survival analysis 10.1 Introduction 10.2 A spatial microeconometric model for firm demography 10.2.1 A spatial model for firm demography 10.2.1.1 Introduction 10.2.1.2 The birth model 10.2.1.3 The growth model 10.2.1.4 The survival model 10.2.2 A case study 10.2.2.1 Data description 10.2.2.2 The birth model 10.2.2.3 The growth model 10.2.2.4 The survival model 10.2.3 Conclusions 10.3 A spatial microeconometric model for firm survival 10.3.1 Introduction 10.3.2 Basic survival analysis techniques 10.3.3 Case study: The survival of pharmaceutical and medical device manufacturing start-up firms in Italy 10.3.3.1 Data description 10.3.3.2 Definition of the spatial microeconometric covariates 10.3.3.3 Definition of the control variables 10.3.3.4 Empirical results 10.4 Conclusion Appendices Appendix 1: Some publicly available spatial datasets Appendix 2: Creation of a W matrix and preliminary computations Appendix 3: Spatial linear models Appendix 4: Non-linear spatial models Appendix 5: Space–time models Appendix 6: Preliminary definitions and concepts in point pattern analysis Appendix 6.1: Point pattern datasets Appendix 6.2: Simulating point patterns Appendix 6.2.1: Homogeneous Poisson processes Appendix 6.2.2: Inhomogeneous Poisson processes Appendix 6.2.3: Cox processes Appendix 6.2.4: Poisson cluster processes Appendix 6.2.5: Regular processes Appendix 6.3: Quadrat-based analysis Appendix 6.4: Clark–Evans test Appendix 7: Models of the spatial location of individuals Appendix 7.1: K-function-based CSR test Appendix 7.2: Point process parameters estimation by the method of minimum contrast Appendix 8: Points in a heterogeneous space Appendix 8.1: D-function-based test of spatial interactions Appendix 8.2: K -function-based test of spatial inhom interactions Appendix 8.3: Duranton–Overman K-density and Marcon–Puech M-function Appendix 9: Space–time models Appendix 9.1: Space–time K-function Appendix 9.2: Gabriel and Diggle’s STIK-function Bibliography Index