3rd Edition
Spatial Data Analysis in Ecology and Agriculture Using R
Preface to the First Edition
Preface to the Second Edition
Preface to the Third Edition
About the Author
Chapter 1 Working with Spatial Data
1.1 Introduction
1.2 Analysis of Spatial Data
1.3 The Data Sets Analyzed in this Book
1.4 Objectives of Data Analysis
1.5 Further Reading
Chapter 2 The R Programming Environment
2.1 Introduction
2.2 R Basics
2.3 Programming Concepts
2.4 Handling Data in R
2.5 Writing Functions in R
2.6 Graphics in R
2.7 Continuing on from Here with R
2.8 Further Reading
2.9 Exercises
Chapter 3 Statistical Properties of Spatially Autocorrelated Data
3.1 Introduction
3.2 Components of a Spatial Random Process
3.3 Monte Carlo Simulation
3.4 A Review of Hypothesis and Significance Testing
3.5 Modeling Spatial Autocorrelation
3.6 Application to Field Data
3.7 Further Reading
3.8 Exercises
Chapter 4 Measures of Spatial Autocorrelation
4.1 Introduction
4.2 Preliminary Considerations
4.3 Join-Count Statistics
4.4 Moran’s I and Geary’s C
4.5 Measures of Autocorrelation Structure
4.6 Measuring Autocorrelation of Spatially Continuous Data
4.7 Further Reading
4.8 Exercises
Chapter 5 Sampling and Data Collection
5.1 Introduction
5.2 Quantifying Sampling Methods
5.3 Developing the Sampling Patterns
5.4 Methods for Variogram Estimation
5.5 Estimating the Sample Size
5.6 Sampling for Thematic Mapping
5.7 Design-Based and Model-Based Sampling
5.8 Further Reading
5.9 Exercises
Chapter 6 Acquisition and Analysis of Remotely Sensed Data
6.1 Introduction
6.2 Fundamentals of Remote Sensing
6.3 Acquisition of Satellite Data
6.4 Display of Remotely Sensed Data
6.5 Introduction to the Analysis of Remotely Sensed Data
6.6 Analysis of Remotely Sensed Data Using Image Segmentation
6.7 Further Reading
6.8 Exercises
Chapter 7 Preparing Spatial Data for Analysis
7.1 Introduction
7.2 Quality of Attribute Data
7.3 Spatial Interpolation Procedures
7.4 Spatial Rectification and Alignment of Data
7.5 Further Reading
7.6 Exercises
Chapter 8 Preliminary Exploration of Spatial Data
8.1 Introduction
8.2 Data Set 1
8.3 Data Set 2
8.4 Data Set 3
8.5 Data Set 4
8.6 Further Reading
8.7 Exercises
Chapter 9 Nonspatial Methods: Linear and Additive Models
9.1 Introduction
9.2 Multiple Linear Regression
9.3 Building a Multiple Regression Model for Field 4.1
9.4 Generalized Linear Models
9.5 The Generalized Additive Model
9.6 Further Reading
9.7 Exercises
Chapter 10 Variance Estimation, the Effective Sample Size, and the Bootstrap
10.1 Introduction
10.2 Bootstrap Estimation of the Standard Error
10.3 Bootstrapping Time Series Data
10.4 Bootstrapping Spatial Data
10.5 Application to the EM38 Data
10.6 Further Reading
10.7 Exercises
Chapter 11 Measures of Bivariate Association between Two Spatial Variables
11.1 Introduction
11.2 Estimating and Testing the Correlation Coefficient
11.3 Contingency Tables
11.4 The Mantel and Partial Mantel Statistics
11.5 The Modifiable Areal Unit Problem and the Ecological Fallacy
11.6 Further Reading
11.7 Exercises
Chapter 12 Machine Learning Methods 1: Recursive Partitioning
12.1 Introduction
12.2 Classification and Regression Trees (a.k.a. Recursive Partitioning)
12.3 Random Forest
12.4 Gradient Boosting
12.5 Further Reading
12.6 Exercises
Chapter 13 Machine Learning 2: Supervised Classification Methods
13.1 Introduction
13.2 The K Nearest Neighbor Method
13.3 Spatial Data Analysis with Support Vector Machines
13.4 Comparison of Supervised Classification Methods
13.5 Further Reading
13.6 Exercises
Chapter 14 The Mixed Model
14.1 Introduction
14.2 Basic Properties of the Mixed Model
14.3 Application to Data Set 3
14.4 Incorporating Spatial Autocorrelation
14.5 Generalized Least Squares
14.6 Spatial Logistic Regression
14.7 Further Reading
Chapter 15 Regression Models for Spatially Autocorrelated Data
15.1 Introduction
15.2 Detecting Spatial Autocorrelation in a Regression Model
15.3 Moran Eigenvector Spatial Filtering
15.4 Models for Spatial Processes
15.5 Determining the Appropriate Regression Model
15.6 Fitting the Spatial Lag and Spatial Error Models
15.7 The Conditional Autoregressive Model
15.8 Application of SAR and CAR Models to Field Data
15.9 Further Reading
15.10 Exercises
Chapter 16 Assembling Conclusions
16.1 Introduction
16.2 Data Set 1
16.3 Data Set 2
16.4 Data Set 3
16.5 Data Set 4
16.6 Conclusions
Appendix A: Review of Mathematical Concepts
A.1 Matrix Theory and Linear Algebra
A.2 Linear Regression
A.3 Nested Models and the General Linear Test
A.4 The Method of Lagrange Multipliers
A.5 The Maximum Likelihood Method
A.6 Change of Variables of a Probability Density
References
Index
Biography
Richard E. Plant is a Professor Emeritus of Plant Sciences and Biological and Agricultural Engineering at the University of California, Davis. He is the co-author of Knowledge-Based Systems in Agriculture and is a former Editor-in-Chief of Computers and Electronics in Agriculture and Associate Editor of Precision Agriculture. He has published extensively on applications of crop modeling, expert systems, spatial statistics, remote sensing, and geographic information systems to problems in crop production and natural resource management.
"Given the widespread availability of large, georeferenced datasets, now is the time for analysts to consider specialized statistical techniques to accommodate spatial autocorrelation and reach valid conclusions about relationships between various attributes. Richard Plant’s third edition of “Spatial Analysis in Ecology and Agriculture using R” revisits the research progress in the field of spatial statistics, covering a variety of modeling approaches that will prove to be highly useful to the intelligent non-specialist. Methods are explained in great detail and illustrated with updated R computer code and results from several different application areas. Scientists, researchers, and related professionals who work with georeferenced data will benefit greatly from this highly instructive, readable book."
Dan S. Long, Research Agronomist (Emeritus), USDA-ARS Soil and Water Conservation Research, USA
