Data Analysis and Statistics for Geography, Environmental Science, and Engineering

By Miguel F. Acevedo

© 2012 – CRC Press

557 pages | 320 B/W Illus.

Purchasing Options:
Hardback: 9781439885017
pub: 2012-12-06
US Dollars$109.95

Comp Exam Copy

About the Book

Providing a solid foundation for twenty-first-century scientists and engineers, Data Analysis and Statistics for Geography, Environmental Science, and Engineering guides readers in learning quantitative methodology, including how to implement data analysis methods using open-source software. Given the importance of interdisciplinary work in sustainability, the book brings together principles of statistics and probability, multivariate analysis, and spatial analysis methods applicable across a variety of science and engineering disciplines.

Learn How to Use a Variety of Data Analysis and Statistics Methods

Based on the author’s many years of teaching graduate and undergraduate students, this textbook emphasizes hands-on learning. Organized into two parts, it allows greater flexibility using the material in various countries and types of curricula. The first part covers probability, random variables and inferential statistics, applications of regression, time series analysis, and analysis of spatial point patterns. The second part uses matrix algebra to address multidimensional problems. After a review of matrices, it delves into multiple regression, dependent random processes and autoregressive time series, spatial analysis using geostatistics and spatial regression, discriminant analysis, and a variety of multivariate analyses based on eigenvector methods.

Build from Fundamental Concepts to Effective Problem Solving

Each chapter starts with conceptual and theoretical material to give a firm foundation in how the methods work. Examples and exercises illustrate the applications and demonstrate how to go from concepts to problem solving. Hands-on computer sessions allow students to grasp the practical implications and learn by doing. Throughout, the computer examples and exercises use seeg and RcmdrPlugin.seeg, open-source R packages developed by the author, which help students acquire the skills to implement and conduct analysis and to analyze the results.

This self-contained book offers a unified presentation of data analysis methods for more effective problem solving. With clear, easy-to-follow explanations, the book helps students to develop a solid understanding of basic statistical analysis and prepares them for learning the more advanced and specialized methods they will need in their work.

Table of Contents

PART I Introduction to Probability, Statistics, Time Series, and Spatial Analysis


Brief History of Statistical and Probabilistic Analysis



Types of Variables

Probability Theory and Random Variables


Descriptive Statistics

Inferential Statistics

Predictors, Models, and Regression

Time Series

Spatial Data Analysis

Matrices and Multiple Dimensions

Other Approaches: Process-Based Models

Baby Steps: Calculations and Graphs


Computer Session: Introduction to R

Supplementary Reading

Probability Theory

Events and Probabilities

Algebra of Events


Probability Trees

Conditional Probability

Testing Water Quality: False Negative and False Positive

Bayes’ Theorem

Generalization of Bayes’ Rule to Many Events


Decision Making


Computer Session: Introduction to Rcmdr, Programming, and Multiple Plots

Supplementary Reading

Random Variables, Distributions, Moments, and Statistics

Random Variables



Some Important RV and Distributions

Application Examples: Species Diversity

Central Limit Theorem

Random Number Generation


Computer Session: Probability and Descriptive Statistics

Example Binomial

Supplementary Reading

Exploratory Analysis and Introduction to Inferential Statistics

Exploratory Data Analysis (EDA)

Relationships: Covariance and Correlation

Statistical Inference

Statistical Methods

Parametric Methods

Nonparametric Methods


Computer Session: Exploratory Analysis and Inferential Statistics

Supplementary Reading

More on Inferential Statistics: Goodness of Fit, Contingency Analysis, and Analysis of Variance

Goodness of Fit (GOF)

Counts and Proportions

Contingency Tables and Cross-Tabulation

Analysis of Variance


Computer Session: More on Inferential Statistics

Supplementary Reading


Simple Linear Least Squares Regression

ANOVA as Predictive Tool

Nonlinear Regression

Computer Session: Simple Regression

Supplementary Reading

Stochastic or Random Processes and Time Series

Stochastic Processes and Time Series: Basics


Autocovariance and Autocorrelation

Periodic Series, Filtering, and Spectral Analysis

Poisson Process

Marked Poisson Process



Computer Session: Random Processes and Time Series

Supplementary Reading

Spatial Point Patterns

Types of Spatially Explicit Data

Types of Spatial Point Patterns

Spatial Distribution

Testing Spatial Patterns: Cell Count Methods

Nearest-Neighbor Analysis

Marked Point Patterns

Geostatistics: Regionalized Variables

Variograms: Covariance and Semivariance


Variogram Models


Computer Session: Spatial Analysis

Supplementary Reading

PART II Matrices, Tempral and Spatial Autoregressive Processes, and Multivariate Analysis

Matrices and Linear Algebra


Dimension of a Matrix


Square Matrices

Matrix Operations

Solving Systems of Linear Equations

Linear Algebra Solution of the Regression Problem

Alternative Matrix Approach to Linear Regression


Computer Session: Matrices and Linear Algebra

Supplementary Reading

Multivariate Models

Multiple Linear Regression

Multivariate Regression

Two-Group Discriminant Analysis

Multiple Analysis of Variance (MANOVA)


Computer Session: Multivariate Models

Supplementary Reading

Dependent Stochastic Processes and Time Series


Semi-Markov Processes

Autoregressive (AR) Process

ARMA and ARIMA Models


Computer Session: Markov Processes and Autoregressive Time Series

Supplementary Reading

Geostatistics: Kriging


Ordinary Kriging

Universal Kriging

Data Transformations


Computer Session: Geostatistics, Kriging

Supplementary Reading

Spatial Auto-Correlation and Auto-Regression

Lattice Data: Spatial Auto-Correlation and Auto-Regression

Spatial Structure and Variance Inflation

Neighborhood Structure

Spatial Auto-Correlation

Spatial Auto-Regression


Computer Session: Spatial Correlation and Regression

Supplementary Reading

Multivariate Analysis I: Reducing Dimensionality

Multivariate Analysis: Eigen-Decomposition

Vectors and Linear Transformation

Eigenvalues and Eigenvectors

Eigen-Decomposition of a Covariance Matrix

Principal Components Analysis (PCA)

Singular Value Decomposition and Biplots

Factor Analysis

Correspondence Analysis


Computer Session: Multivariate Analysis, PCA

Supplementary Reading

Multivariate Analysis II: Identifying and Developing Relationships among Observations and Variables


Multigroup Discriminant Analysis (MDA)

Canonical Correlation

Constrained (or Canonical) Correspondence Analysis (CCA)

Cluster Analysis

Multidimensional Scaling (MDS)


Computer Session: Multivariate Analysis II

Supplementary Reading



About the Author

Miguel F. Acevedo has 38 years of academic experience, the last 20 of these as faculty member of the University of North Texas (UNT). His career has been interdisciplinary, especially at the interface of science and engineering. He obtained his Ph.D. in biophysics from the University of California Berkeley and master's degrees in electrical engineering and computer science from Berkeley and the University of Texas at Austin, respectively. Prior to UNT, he was at the Universidad de Los Andes in Merida, Venezuela, where he taught for 18 years. He has served on the Science Advisory Board of the U.S. Environmental Protection Agency and on many review panels of the U.S. National Science Foundation. He has received numerous research grants and written many journal articles, book chapters, and proceedings articles. UNT has recognized him with the Regent’s Professor rank, the Citation for Distinguished Service to International Education, and the Regent’s Faculty Lectureship. For more information, see Dr. Acevedo’s page at UNT.

Subject Categories

BISAC Subject Codes/Headings:
MATHEMATICS / Probability & Statistics / General
SCIENCE / Environmental Science