Spatial Data Analysis in Ecology and Agriculture Using R

Assuming no prior knowledge of R, Spatial Data Analysis in Ecology and Agriculture Using R provides practical instruction on the use of the R programming language to analyze spatial data arising from research in ecology and agriculture. Written in terms of four data sets easily accessible online, this book guides the reader through the analysis of each data set, including setting research objectives, designing the sampling plan, data quality control, exploratory and confirmatory data analysis, and drawing scientific conclusions.
Based on the author’s spatial data analysis course at the University of California, Davis, the book is intended for classroom use or self-study by graduate students and researchers in ecology, geography, and agricultural science with an interest in the analysis of spatial data.

Working with Spatial DataAnalysis of Spatial DataData Sets Analyzed in This BookR Programming EnvironmentR BasicsProgramming ConceptsHandling Data in RWriting Functions in RGraphics in ROther Software PackagesStatistical Properties of Spatially Autocorrelated DataComponents of a Spatial Random ProcessMonte Carlo SimulationReview of Hypothesis and Significance TestingModeling Spatial AutocorrelationApplication to Field DataMeasures of Spatial AutocorrelationPreliminary ConsiderationsJoin-Count StatisticsMoran’s I and Geary’s cMeasures of Autocorrelation StructureMeasuring Autocorrelation of Spatially Continuous DataSampling and Data CollectionPreliminary ConsiderationsDeveloping the Sampling PatternsMethods for Variogram EstimationEstimating the Sample SizeSampling for Thematic MappingDesign-Based and Model-Based SamplingPreparing Spatial Data for AnalysisQuality of Attribute DataSpatial Interpolation ProceduresSpatial Rectification and Alignment of DataPreliminary Exploration of Spatial DataData Set 1Data Set 2Data Set 3Data Set 4Multivariate Methods for Spatial Data ExplorationPrincipal Components AnalysisClassification and Regression Trees (aka Recursive Partitioning)Random ForestSpatial Data Exploration via Multiple RegressionMultiple Linear RegressionBuilding a Multiple Regression Model for Field 4.1Generalized Linear ModelsVariance Estimation, the Effective Sample Size, and the BootstrapBootstrap Estimation of the Standard ErrorBootstrapping Time Series DataBootstrapping Spatial DataApplication to the EM38 DataMeasures of Bivariate Association between Two Spatial VariablesEstimating and Testing the Correlation CoefficientContingency TablesMantel and Partial Mantel StatisticsModifiable Areal Unit Problem and Ecological FallacyMixed ModelBasic Properties of the Mixed ModelApplication to Data Set 3Incorporating Spatial AutocorrelationGeneralized Least SquaresSpatial Logistic RegressionRegression Models for Spatially Autocorrelated DataDetecting Spatial Autocorrelation in a Regression ModelModels for Spatial ProcessesDetermining the Appropriate Regression ModelFitting the Spatial Lag and Spatial Error ModelsConditional Autoregressive ModelApplication of SAR and CAR Models to Field DataAutologistic Model for Binary DataBayesian Analysis of Spatially Autocorrelated DataMarkov Chain Monte Carlo MethodsIntroduction to WinBUGSHierarchical ModelsIncorporation of Spatial EffectsAnalysis of Spatiotemporal DataSpatiotemporal Cluster AnalysisFactors Underlying Spatiotemporal Yield ClustersBayesian Spatiotemporal AnalysisOther Approaches to Spatiotemporal ModelingAnalysis of Data from Controlled ExperimentsClassical Analysis of VarianceComparison of MethodsPseudoreplicated Data and the Effective Sample SizeAssembling ConclusionsData Set 1Data Set 2Data Set 3Data Set 4ConclusionsAppendicesReview of Mathematical ConceptsThe Data SetsAn R ThesaurusReferences Index