| |
| |
| |
Introduction | |
| |
| |
| |
Why Numerical Ecology? | |
| |
| |
| |
Why R? | |
| |
| |
| |
Readership and Structure of the Book | |
| |
| |
| |
How to Use This Book | |
| |
| |
| |
The Data Sets | |
| |
| |
| |
The Doubs Fish Data | |
| |
| |
| |
The Oribatid Mite Data | |
| |
| |
| |
A Quick Reminder about Help Sources | |
| |
| |
| |
Now It Is Time | |
| |
| |
| |
Exploratory Data Analysis | |
| |
| |
| |
Objectives | |
| |
| |
| |
Data Exploration | |
| |
| |
| |
Data Extraction | |
| |
| |
| |
Species Data: First Contact | |
| |
| |
| |
Species Data: A Closer Look | |
| |
| |
| |
Species Data Transformation | |
| |
| |
| |
Environmental Data | |
| |
| |
| |
Conclusion | |
| |
| |
| |
Association Measures and Matrices | |
| |
| |
| |
Objectives | |
| |
| |
| |
The Main Categories of Association Measures (Short Overview) | |
| |
| |
| |
Q Mode and R Mode | |
| |
| |
| |
Symmetrical or Asymmetrical Coefficients in Q Mode: The Double-Zero Problem | |
| |
| |
| |
Association Measures for Qualitative or Quantitative Data | |
| |
| |
| |
To Summarize | |
| |
| |
| |
Q Mode: Computing Distance Matrices Among Objects | |
| |
| |
| |
Q Mode: Quantitative Species Data | |
| |
| |
| |
Q Mode: Binary (Presence-Absence) Species Data | |
| |
| |
| |
Q Mode: Quantitative Data (Excluding Species Abundances) | |
| |
| |
| |
Q Mode: Binary Data (Excluding Species Presence-Absence Data) | |
| |
| |
| |
Q Mode: Mixed Types, Including Categorical (Qualitative Multiclass) Variables | |
| |
| |
| |
R Mode: Computing Dependence Matrices Among Variables | |
| |
| |
| |
R Mode: Species Abundance Data | |
| |
| |
| |
R Mode: Species Presence-Absence Data | |
| |
| |
| |
R Mode: Quantitative and Ordinal Data (Other than Species Abundances) | |
| |
| |
| |
R Mode: Binary Data (Other than Species Abundance Data) | |
| |
| |
| |
Pre-transformations for Species Data | |
| |
| |
| |
Conclusion | |
| |
| |
| |
Cluster Analysis | |
| |
| |
| |
Objectives | |
| |
| |
| |
Clustering Overview | |
| |
| |
| |
Hierarchical Clustering Based on Links | |
| |
| |
| |
Single Linkage Agglomerative Clustering | |
| |
| |
| |
Complete Linkage Agglomerative Clustering | |
| |
| |
| |
Average Agglomerative Clustering | |
| |
| |
| |
Ward's Minimum Variance Clustering | |
| |
| |
| |
Flexible Clustering | |
| |
| |
| |
Interpreting and Comparing Hierarchical Clustering Results | |
| |
| |
| |
Introduction | |
| |
| |
| |
Cophenetic Correlation | |
| |
| |
| |
Looking for Interpretable Clusters | |
| |
| |
| |
Non-hierarchical Clustering | |
| |
| |
| |
K-Means Partitioning | |
| |
| |
| |
Partitioning Around Medoids | |
| |
| |
| |
Comparison with Environmental Data | |
| |
| |
| |
Comparing a Typology with External Data (ANOVA Approach) | |
| |
| |
| |
Comparing Two Typologies (Contingency Table Approach) | |
| |
| |
| |
Species Assemblages | |
| |
| |
| |
Simple Statistics on Group Contents | |
| |
| |
| |
Kendall's W Coefficient of Concordance | |
| |
| |
| |
Species Assemblages in Presence-Absence Data | |
| |
| |
| |
IndVal: Species Indicator Values | |
| |
| |
| |
Multivariate Regression Trees: Constrained Clustering | |
| |
| |
| |
Introduction | |
| |
| |
| |
Computation (Principle) | |
| |
| |
| |
Application Using Packages mvpart and MVPARTwrap | |
| |
| |
| |
Combining MRT and IndVal | |
| |
| |
| |
MRT as a �Chronological� Clustering Method | |
| |
| |
| |
A Very Different Approach: Fuzzy Clustering | |
| |
| |
| |
Fuzzy c-Means Clustering Using cluster's Function fanny() | |
| |
| |
| |
Conclusion | |
| |
| |
| |
Unconstrained Ordination | |
| |
| |
| |
Objectives | |
| |
| |
| |
Ordination Overview | |
| |
| |
| |
Multidimensional Space | |
| |
| |
| |
Ordination in Reduced Space | |
| |
| |
| |
Principal Component Analysis | |
| |
| |
| |
Overview | |
| |
| |
| |
PCA on the Environmental Variables of the Doubs Data Set Using rda() | |
| |
| |
| |
PCA on Transformed Species Data | |
| |
| |
| |
Domain of Application of PCA | |
| |
| |
| |
PCA Using Function PCA() | |
| |
| |
| |
Correspondence Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
CA Using Function cca() of Package vegan | |
| |
| |
| |
CA Using Function CA() | |
| |
| |
| |
Arch Effect and Detrended Correspondence Analysis | |
| |
| |
| |
Multiple Correspondence Analysis | |
| |
| |
| |
Principal Coordinate Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Application to the Doubs Data Set Using cmdscale and vegan | |
| |
| |
| |
Application to the Doubs Data Set Using pcoa() | |
| |
| |
| |
Nontnetric Multidimensional Scaling | |
| |
| |
| |
Introduction | |
| |
| |
| |
Application to the Fish Data | |
| |
| |
| |
Handwritten Ordination Function | |
| |
| |
| |
Canonical Ordination | |
| |
| |
| |
Objectives | |
| |
| |
| |
Canonical Ordination Overview | |
| |
| |
| |
Redundancy Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
RDA of the Doubs River Data | |
| |
| |
| |
A Hand-Written RDA Function | |
| |
| |
| |
Canonical Correspondence Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
CCA of the Doubs Data | |
| |
| |
| |
Linear Discriminant Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Discriminant Analysis Using lda() | |
| |
| |
| |
Other Asymmetrical Analyses | |
| |
| |
| |
Symmetrical Analysis of Two (or More) Data Sets | |
| |
| |
| |
Canonical Correlation Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Canonical Correlation Analysis using CCorA | |
| |
| |
| |
Co-inertia Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Co-inertia Analysis Using ade4 | |
| |
| |
| |
Multiple Factor Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Multiple Factor Analysis Using FactoMineR | |
| |
| |
| |
Conclusion | |
| |
| |
| |
Spatial Analysis of Ecological Data | |
| |
| |
| |
Objectives | |
| |
| |
| |
Spatial Structures and Spatial Analysis: A Short Overview | |
| |
| |
| |
Introduction | |
| |
| |
| |
Induced Spatial Dependence and Spatial Autocorrelation | |
| |
| |
| |
Spatial Scale | |
| |
| |
| |
Spatial Heterogeneity | |
| |
| |
| |
Spatial Correlation or Autocorrelation Functions and Spatial Correlograms | |
| |
| |
| |
Testing for the Presence of Spatial Correlation: Conditions | |
| |
| |
| |
Modelling Spatial Structures | |
| |
| |
| |
Multivariate Trend-Surface Analysis | |
| |
| |
| |
Introduction | |
| |
| |
| |
Trend-Surface Analysis in Practice | |
| |
| |
| |
Eigenvector-Based Spatial Variables and Spatial Modelling | |
| |
| |
| |
Introduction | |
| |
| |
| |
Classical Distance-Based MEM, Formerly Called Principal Coordinates of Neighbour Matrices | |
| |
| |
| |
MEM in a Wider Context: Weights Other than Geographic Distances | |
| |
| |
| |
MEM with Positive or Negative Spatial Correlation: Which Ones Should Be Used? | |
| |
| |
| |
Asymmetric Eigenvector Maps: When Directionality Matters | |
| |
| |
| |
Another Way to Look at Spatial Structures: Multiscale Ordination | |
| |
| |
| |
Principle | |
| |
| |
| |
Application to the Mite Data: Exploratory Approach | |
| |
| |
| |
Application to the Detrended Mite and Environmental Data | |
| |
| |
| |
Conclusion | |
| |
| |
Bibliographical References | |
| |
| |
Index | |