Spatial analysis with R : statistics, visualization, and computational methods / Tonny J. Oyana.

Format:

Book

Author/Creator:

Oyana, Tonny J.

Language:

English

Subjects (All):

Spatial analysis (Statistics).

Physical Description:

1 online resource (355 pages) : illustrations

Edition:

Second edition.

Place of Publication:

Abingdon, Oxon : CRC Press, [2021]

Biography/History:

Professor Tonny J. Oyana received his Ph. D. and his postdoctoral training from the University of Buffalo, New York, USA. He currently serves as the College Principal at the Makerere University College of Computing and Information Science, Kampala, Uganda. He has served for over 20 years in several academic positions at the Southern Illinois University Carbondale and University of Tennessee Health Science Center, Memphis, USA. His research focuses on establishing whether there is a link between environmental health and exposure; advancing GIS methods, algorithm design, and spatial analytical methods; and understanding the factors that contribute toward land systems change. He has authored or co-authored more than 100 scientific works.

Summary:

In the five years since the publication of the first edition of Spatial Analysis: Statistics, Visualization, and Computational Methods, many new developments have taken shape regarding the implementation of new tools and methods for spatial analysis with R. The use and growth of artificial intelligence, machine learning and deep learning algorithms with a spatial perspective, and the interdisciplinary use of spatial analysis are all covered in this second edition along with traditional statistical methods and algorithms to provide a concept-based problem-solving learning approach to mastering practical spatial analysis. Spatial Analysis with R: Statistics, Visualization, and Computational Methods, Second Edition provides a balance between concepts and practicums of spatial statistics with a comprehensive coverage of the most important approaches to understand spatial data, analyze spatial relationships and patterns, and predict spatial processes. New in the Second Edition: Includes new practical exercises and worked-out examples using R Presents a wide range of hands-on spatial analysis worktables and lab exercises All chapters are revised and include new illustrations of different concepts using data from environmental and social sciences Expanded material on spatiotemporal methods, visual analytics methods, data science, and computational methods Explains big data, data management, and data mining This second edition of an established textbook, with new datasets, insights, excellent illustrations, and numerous examples with R, is perfect for senior undergraduate and first-year graduate students in geography and the geosciences.

Contents:

Cover

Half Title

Title Page

Copyright Page

Dedication

Contents

Preface

Acknowledgments

Author

1. Understanding the Context and Relevance of Spatial Analysis

Learning Objectives

Introduction

From Data to Information, to Knowledge, and Wisdom

Spatial Analysis Using a GIS Timeline

Spatial Analysis in the Post-1990s Period

Data Science, GIS, and Artificial Intelligence

Geographic Data: Properties, Strengths, and Analytical Challenges

Concept of Scale

Concept of Spatial Dependency

Concept of Spatial Proximity

Modifiable Areal Unit Problem

Concept of Spatial Autocorrelation

Conclusion

Worked Examples in R and Stay One Step Ahead with Challenge Assignments

Working with R

Getting Started

Working with Spatial Data

Tips for Working with R

Stay One Step Ahead with Challenge Assignments

Review and Study Questions

Glossary of Key Terms

References

2. Making Scientific Observations and Measurements in Spatial Analysis

Scales of Measurement

Nominal Scale

Ordinal Scale

Interval Scale

Ratio Scale

Two Main Approaches for Data Collection That Involve Deductive and Inductive Reasoning

Population and Sample

Spatial Sampling

Step I. View Data Structure

Step II. Basic Data Summaries

Step III. Exploring the Spatial Data

3. Using Statistical Measures to Analyze Data Distributions

Descriptive Statistics

Measures of Central Tendency

Deriving a Weighted Mean Using the Frequency Distributions in a Set of Observations

Measures of Dispersion.

Spatial Statistics: Measures for Describing Basic Characteristics of Spatial Data

Spatial Measures of Central Tendency

Spatial Measures of Dispersion

Random Variables and Probability Distribution

Random Variable

Probability and Theoretical Data Distributions

Concepts and Applications

Binomial Distribution

Poisson Distribution

Normal Distribution

Exploring Z-Score to Assess the Relative Position in Data Distributions Using R

4. Engaging in Exploratory Data Analysis, Visualization, and Hypothesis Testing

Exploratory Data Analysis, Geovisualization, and Data Visualization Methods

Data Visualization

Geographic Visualization

New Stunning Visualization Tools and Infographics

Exploratory Approaches for Visualizing Spatial Datasets

Visualizing Multidimensional Datasets: An Illustration Based on U.S. Educational Achievements Rates, 1970-2012

Hypothesis Testing, Confidence Intervals, and .p.-Values

Computation

Statistical Conclusion

Generating Graphical Data Summaries

5. Understanding Spatial Statistical Relationships

Engaging in Correlation Analysis

Ordinary Least Squares and Geographically Weighted Regression Methods

Procedures in Developing a Spatial Regression Model

Examining Relationships between Regression Variables.

Examining the Strength of Association and Direction of All Paired Variables Using a Scatterplot Matrix

Fitting the Ordinary Least Squares Regression Model

Primary Model

Examining Variance Inflation Factor Results

Reduced Model

Best Model

Examining Residual Changes in Ordinary Least Squares Regression Models

Fitting the Geographically Weighted Regression Model

Examining Residual Change and Effects of Predictor Variables on Local Areas

Summary of Modeling Result

6. Engaging in Point Pattern Analysis

Rationale for Studying Point Patterns and Distributions

Exploring Patterns, Distributions, and Trends Associated with Point Features

Quadrat Count

Nearest Neighbor Approach

K-Function Approach

Kernel Estimation Approach

Constructing a Voronoi Map from Point Features

Exploring Space-Time Patterns

Conclusions

Explore Potential Path Area and Activity Space Concepts

7. Engaging in Areal Pattern Analysis Using Global and Local Statistics

Rationale for Studying Areal Patterns

The Notion of Spatial Relationships

Quantifying Spatial Autocorrelation Effects in Areal Patterns

Join Count Statistics

Interpreting the Join Count Statistics and Methodological Flaws

Global Moran's I Coefficient of Spatial Autocorrelation

Interpreting Moran's I and Methodological Flaws

Global Geary's C Coefficient of Spatial Autocorrelation.

Interpreting Geary's C and Methodological Flaws

Getis-Ord G Statistics

Interpretation of Getis-Ord G and Methodological Flaws

Local Moran's I

Local G-Statistic

Local Geary

Using Scatterplots to Synthesize and Interpret Local Indicators of Spatial Association Statistics

Quiz

8. Engaging in Geostatistical Analysis

Rationale for Using Geostatistics to Study Complex Spatial Patterns

Basic Interpolation Equations

Spatial Structure Functions for Regionalized Variables

Kriging Method and Its Theoretical Framework

Simple Kriging

Ordinary Kriging

Universal Kriging

Indicator Kriging

Key Points to Note about the Geostatistical Estimation Using Kriging

Exploratory Data Analysis

Spatial Prediction and Modeling

Uncertainty Analysis

Conditional Geostatistical Simulation

Inverse Distance Weighting

9. Data Science: Understanding Computing Systems and Analytics for Big Data

Introduction to Data Science

Rationale for a Big Geospatial Data Framework

Data Management

Data Warehousing

Data Sources, Processing Tools, and the Extract-Transform-Load Process

Data Integration and Storage

Data-Mining Algorithms for Big Geospatial Data

Tools, Algorithms, and Methods for Data Mining and Actionable Knowledge

Business Intelligence, Spatial Online Analytical Processing, and Analytics

Analytics and Strategies for Big Geospatial Data

Spatiotemporal Data Analytics.

Classification Algorithms for Detecting Clusters in Big Geospatial Data

Embedding Solutions/Algorithm with Topological Considerations

Graph and Text Analytics

Index.

Notes:

"First edition published 2015."

Includes bibliographical references and index.

Description based on print version record.

ISBN:

1-00-302164-6

1-000-17347-X

1-003-02164-6

1-000-17345-3

9781003021643

OCLC:

1195825512