Data analysis in vegetation ecology / Otto Wildi

Incluye bibliografía: páginas 281-291 e índice: páginas 297-301

Preface to the second edition.. Preface to the first edition.. List of figures.. List of tables.. About the companion website.. 1 Introduction.. 2 Patterns in vegetation ecology.. 2.1 Pattern recognition.. 2.2 Interpretation of patterns.. 2.3 Sampling for pattern recognition.. 2.3.1 Getting a sample.. 2.3.2 Organizing the data.. 2.4 Pattern recognition in R.. 3 Transformation.. 3.1 Data types.. 3.2 Scalar transformation and the species enigma.. 3.3 Vector transformation.. 3.4 Example: Transformation of plant cover data.. 4 Multivariate comparison.. 4.1 Resemblance in multivariate space.. 4.2 Geometric approach.. 4.3 Contingency measures.. 4.4 Product moments.. 4.5 The resemblance matrix.. 4.6 Assessing the quality of classifications.. 5 Classification.. 5.1 Group structures.. 5.2 Linkage clustering.. 5.3 Average linkage clustering.. 5.4 Minimum-variance clustering.. 5.5 Forming groups.. 5.6 Silhouette plot and fuzzy representation.. 6 Ordination.. 6.1 Why ordination?.. 6.2 Principal component analysis.. 6.3 Principal coordinates analysis.. 6.4 Correspondence analysis.. 6.5 Heuristic ordination.. 6.5.1 The horseshoe or arch effect.. 6.5.2 Flexible shortest path adjustment.. 6.5.3 Nonmetric multidimensional scaling.. 6.5.4 Detrended correspondence analysis.. 6.6 How to interpret ordinations.. 6.7 Ranking by orthogonal components.. 6.7.1 RANK method.. 6.7.2 A sampling design based on RANK (example.. 7 Ecological patterns.. 7.1 Pattern and ecological response.. 7.2 Evaluating groups.. 7.2.1 Variance testing.. 7.2.2 Variance ranking.. 7.2.3 Ranking by indicator values.. 7.2.4 Contingency tables.. 7.3 Correlating spaces.. 7.3.1 The Mantel test.. 7.3.2 Correlograms.. 7.3.3 More trends: 'Schlaenggli' data revisited.. 7.4 Multivariate linear models.. 7.4.1 Constrained ordination.. 7.4.2 Nonparametric multiple analysis of variance.. 7.5 Synoptic vegetation tables.. 7.5.1 The aim of ordering tables

7.5.2 Steps involved in sorting tables.. 7.5.3 Example: ordering Ellenberg's data.. 8 Static predictive modelling.. 8.1 Predictive or explanatory?.. 8.2 Evaluating environmental predictors.. 8.3 Generalized linear models.. 8.4 Generalized additive models.. 8.5 Classification and regression trees.. 8.6 Building scenarios.. 8.7 Modelling vegetation types.. 8.8 Expected wetland vegetation (example.. 9 Vegetation change in time.. 9.1 Coping with time.. 9.2 Temporal autocorrelation.. 9.3 Rate of change and trend.. 9.4 Markov models.. 9.5 Space-for-time substitution.. 9.5.1 Principle and method.. 9.5.2 The Swiss National Park succession (example.. 9.6 Dynamics in pollen diagrams (example.. 10 Dynamic modelling.. 10.1 Simulating time processes.. 10.2 Simulating space processes.. 10.3 Processes in the Swiss National Park.. 10.3.1 The temporal model.. 10.3.2 The spatial model.. 11 Large data sets: wetland patterns.. 11.1 Large data sets differ.. 11.2 Phytosociology revisited.. 11.3 Suppressing outliers.. 11.4 Replacing species with new attributes.. 11.5 Large synoptic tables?.. 12 Swiss forests: a case study.. 12.1 Aim of the study.. 12.2 Structure of the data set.. 12.3 Selected questions.. 12.3.1 Is the similarity pattern discrete or continuous?.. 12.3.2 Is there a scale effect from plot size?.. 12.3.3 Does the vegetation pattern reflect environmental conditions?.. 12.3.4 Is tree species distribution man-made?.. 12.3.5 Is the tree species pattern expected to change?.. 12.4 Conclusions.. Bibliography.. Appendix A Functions in package dave.. Appendix B Data sets used.. Index

The first edition of Data Analysis in Vegetation Ecology provided an accessible and thorough resource for evaluating plant ecology data, based on the author's extensive experience of research and analysis in this field. Now, the Second Edition expands on this by not only describing how to analyse data, but also enabling readers to follow the step-by-step case studies themselves using the freely available statistical package R. The addition of R in this new edition has allowed coverage of additional methods for classification and ordination, and also logistic regression, GLMs, GAMs, regression trees as well as multinomial regression to simulate vegetation types. A package of statistical functions, specifically written for the book, covers topics not found elsewhere, such as analysis and plot routines for handling synoptic tables. All data sets presented in the book are now also part of the R package 'dave', which is freely available online at the R Archive webpage. The book and data analysis tools combined provide a complete and comprehensive guide to carrying out data analysis students, researchers and practitioners in vegetation science and plant ecology. A completely revised and updated edition of this popular introduction to data analysis in vegetation ecology • Now includes practical examples using the freely available statistical package 'R' • Written by a world renowned expert in the field. • Complex concepts and operations are explained using clear illustrations and case studies relating to real world phenomena. • Highlights both the potential and limitations of the methods used, and the final interpretations. • Gives suggestions on the use of the most widely used statistical software in vegetation ecology and how to start analysing data. eng