The second edition of the book Spatial Analysis with R: Statistics, Visualization, and Computational Methods by Tonny J. Oyana was published by CRC Press in 2021. The book contains nine chapters and 339 pages. According to the author, since the last edition, new tools and techniques including machine learning and deep learning algorithms, artificial intelligence (AI), and new R scripts have been developed with increased attention to spatial processes and analysis. The book provides a good balance between theory and examples on traditional statistical and spatial analysis using R sample code. Each chapter starts with the learning objectives and also includes conclusions, and review and study questions.

Chapter 1 introduces readers to the developments in spatial analysis concepts. It explains briefly concept of scale, spatial dependency, proximity, and spatial autocorrelation. Spatial data collection is a tricky process and it involves a careful selection of sampling strategy and a framework for good quality data gathering. Chapter 2 deals with clarifying differences between sample and population, scales of measurement, various sampling strategies, and spatial data processing. Chapter 3 presents statistical measures used to analyze measured data distributions. These include measures of central tendency and dispersion for both descriptive statistics and spatial statistics, as well as probability distribution. Exploratory data analysis, visualization, hypothesis testing, confidence intervals, and p values are explained in Chapter 4. The visualization of multidimensional datasets and tools are described in sufficient detail in this chapter. Use of parallel coordinate plots is useful to gain further insight into the data and was dealt with using four options of no scaling, scaling, scaling by normalizing, and scaling by standardizing and centering.

Chapter 5 introduces multivariate analysis and spatial statistical relationships. This chapter deals with running various commonly used spatial regression models, R codes, and interpretation of the regression analysis. The chapter provides a detailed explanation on describing and interpreting overall spatial patterns. The approaches for quantifying patterns of distribution are given in next two chapters. Chapter 6 deals with point pattern analysis, while Chapter 7 deals with areal pattern analysis using global and local statistics. The spatial dependency and autocorrelation analysis at local and global scales is discussed in the Chapter 7. The chapter also explains various required assumptions and criteria for conducting a vigorous spatial analysis. Chapter 8 presents the rationale for using geospatial analysis, various standard kriging methods and tools, deterministic and stochastic approaches, spatial predictions and modeling, variograms, and conditional geostatistical simulations. The chapter also discusses how to account for secondary factors to make sound decisions on spatial scales.

The big data analysis and understanding of computing systems is presented in the Chapter 9. The chapter provides an introduction to data science, especially large-scale datasets and emerging technology. The chapter also explores future trends and directions for spatial analysis of large datasets for reducing the gaps in knowledge.

Overall, the book provides a detailed explanation on hypothesis testing, traditional and spatial data science and modeling, big data interpretation and handling, and three-dimensional visualization of trends in the data. Examples presented in the book are not always from STEM (science, technology, engineering and mathematics) fields; instead, they can be grasped by a much wider audiences. The worked examples with R are very useful for students especially for beginners, although some of the students may benefit more from reading books such as R scripts for beginners. This book is useful and I will recommend it for students, researchers, and practitioners involved in the big data analysis as well as traditional statistical and geospatial analysis.

Tonny J. Oyana所著的《Spatial Analysis with R: Statistics, Visualization, and Computational Methods 》一书第二版于 2021 年由 CRC Press 出版。该书共 9 章，339 页。据作者介绍，自上一版以来，随着对空间过程和分析的日益关注，包括机器学习和深度学习算法、人工智能 (AI) 和新 R 脚本在内的新工具和技术得到了开发。本书在使用 R 示例代码进行传统统计和空间分析的理论和示例之间提供了良好的平衡。每章都从学习目标开始，还包括结论、复习和研究问题。

第 1 章向读者介绍了空间分析概念的发展。它简要解释了尺度、空间相关性、邻近性和空间自相关的概念。空间数据收集是一个棘手的过程，它涉及仔细选择抽样策略和高质量数据收集框架。第 2 章阐明样本与总体之间的差异、测量尺度、各种抽样策略和空间数据处理。第 3 章介绍了用于分析测量数据分布的统计测量。这些包括对描述性统计和空间统计以及概率分布的集中趋势和分散的度量。探索性数据分析、可视化、假设检验、置信区间和p第 4 章解释了这些值。本章详细描述了多维数据集和工具的可视化。平行坐标图的使用有助于进一步了解数据，并使用四个选项进行处理：不缩放、缩放、归一化缩放以及标准化和居中缩放。

第5章介绍多元分析和空间统计关系。本章涉及运行各种常用的空间回归模型、R 代码和回归分析的解释。本章详细解释了对整体空间格局的描述和解释。在接下来的两章中给出了量化分布模式的方法。第 6 章涉及点模式分析，而第 7 章涉及使用全局和局部统计的区域模式分析。第 7 章讨论了局部和全球尺度的空间依赖性和自相关分析。本章还解释了进行有力空间分析所需的各种假设和标准。第 8 章介绍了使用地理空间分析的基本原理，各种标准克里金法和工具、确定性和随机方法、空间预测和建模、变异函数和条件地质统计模拟。本章还讨论了如何考虑次要因素以在空间尺度上做出合理的决策。

第 9 章介绍了计算系统的大数据分析和理解。该章介绍了数据科学，尤其是大规模数据集和新兴技术。本章还探讨了大型数据集空间分析的未来趋势和方向，以缩小知识差距。

总体而言，本书对假设检验、传统和空间数据科学与建模、大数据解释和处理以及数据趋势的三维可视化提供了详细的解释。书中提供的示例并不总是来自 STEM（科学、技术、工程和数学）领域；相反，它们可以被更广泛的受众所掌握。使用 R 编写的示例对学生特别是初学者非常有用，尽管一些学生可能会从阅读 R 脚本等初学者书籍中受益更多。这本书很有用，我会向参与大数据分析以及传统统计和地理空间分析的学生、研究人员和从业人员推荐它。