Analyzing Ecological Data (eBook)

Alain Zuur, Elena N. Ieno, Graham M. Smith (Autoren)

eBook Download: PDF

2007 | 2007
XXVI, 672 Seiten
Springer New York (Verlag)
978-0-387-45972-1 (ISBN)

Infos

This book provides a practical introduction to analyzing ecological data using real data sets. The first part gives a largely non-mathematical introduction to data exploration, univariate methods (including GAM and mixed modeling techniques), multivariate analysis, time series analysis, and spatial statistics. The second part provides 17 case studies. The case studies include topics ranging from terrestrial ecology to marine biology and can be used as a template for a reader's own data analysis. Data from all case studies are available from www.highstat.com. Guidance on software is provided in the book.

Grad students, researchers

---

'Which test should I apply?' During the many years of working with ecologists, biologists and other environmental scientists, this is probably the question that the authors of this book hear the most often. The answer is always the same and along the lines of 'What are your underlying questions?', 'What do you want to show?'. The answers to these questions provide the starting point for a detailed discussion on the ecological background and purpose of the study. This then gives the basis for deciding on the most appropriate analytical approach. Therefore, a better start- ing point for an ecologist is to avoid the phrase 'test' and think in terms of 'analy- sis'. A test refers to something simple and unified that gives a clear answer in the form of a p-value: something rarely appropriate for ecological data. In practice, one has to apply a data exploration, check assumptions, validate the models, per- haps apply a series of methods, and most importantly, interpret the results in terms of the underlying ecology and the ecological questions being investigated. Ecology is a quantitative science trying to answer difficult questions about the complex world we live in. Most ecologists are aware of these complexities, but few are fully equipped with the statistical sophistication and understanding to deal with them.

Inhalt

Preface 7
Contents 10
Contributors 17
1 Introduction 25
1.1 Part 1: Applied statistical theory 25
1.2 Part 2: The case studies 27
1.3 Data, software and flowcharts 30
2 Data management and software 31
2.1 Introduction 31
2.2 Data management 32
2.3 Data preparation 33
2.4 Statistical software 37
3 Advice for teachers 41
3.1 Introduction 41
4 Exploration 47
4.1 The first steps 48
4.2 Outliers, transformations and standardisations 62
4.3 A final thought on data exploration 71
5 Linear regression 73
5.1 Bivariate linear regression 73
5.2 Multiple linear regression 91
5.3 Partial linear regression 97
6 Generalised linear modelling 102
6.1 Poisson regression 102
6.2 Logistic regression 111
7 Additive and generalised additive modelling 120
7.1 Introduction 120
7.2 The additive model 124
7.3 Example of an additive model 125
7.4 Estimate the smoother and amount of smoothing 127
7.5 Additive models with multiple explanatory variables 131
7.6 Choosing the amount of smoothing 135
7.7 Model selection and validation 138
7.8 Generalised additive modelling 143
7.9 Where to go from here 147
8 Introduction to mixed modelling 148
8.1 Introduction 148
8.2 The random intercept and slope model 151
8.3 Model selection and validation 153
8.4 A bit of theory 158
8.5 Another mixed modelling example 160
8.6 Additive mixed modelling 163
9 Univariate tree models 166
9.1 Introduction 166
9.2 Pruning the tree 172
9.3 Classification trees 175
9.4 A detailed example: Ditch data 175
10 Measures of association 185
10.1 Introduction 185
10.2 Association between sites: Q analysis 186
10.3 Association among species: R analysis 193
10.4 Q and R analysis: Concluding remarks 198
10.5 Hypothesis testing with measures of association 201
11 Ordination — First encounter 210
11.1 Bray- Curtis ordination 210
12 Principal component analysis and redundancy analysis 214
12.1 The underlying principle of PCA 214
12.2 PCA: Two easy explanations 215
12.3 PCA: Two technical explanations 217
12.4 Example of PCA 218
12.5 The biplot 221
12.6 General remarks 226
12.7 Chord and Hellinger transformations 227
12.8 Explanatory variables 229
12.9 Redundancy analysis 231
12.10 Partial RDA and variance partitioning 240
12.11 PCA regression to deal with collinearity 242
13 Correspondence analysis and canonical correspondence analysis 246
13.1 Gaussian regression and extensions 246
13.2 Three rationales for correspondence analysis 252
13.3 From RGR to CCA 259
13.4 Understanding the CCAtriplot 261
13.5 When to use PCA, CA, RDA or CCA 263
13.6 Problems with CA and CCA 264
14 Introduction to discriminant analysis 266
14.1 Introduction 266
14.2 Assumptions 269
14.3 Example 271
14.4 The mathematics 275
14.5 The numerical output for the sparrow data 276
15 Principal coordinate analysis and non-metric multidimensional scaling 280
15.1 Principal coordinate analysis 280
15.2 Non-metric multidimensional scaling 282
16 Time series analysis — Introduction 286
16.1 Using what we have already seen before 286
16.2 Auto-regressive integrated moving average models with exogenous variables 302
17 Common trends and sudden changes 310
17.1 Repeated LOESS smoothing 310
17.2 Identifying the seasonal component 314
17.3 Common trends: MAFA 320
17.4 Common trends: Dynamic factor analysis 324
17.5 Sudden changes: Chronological clustering 336
18 Analysis and modelling of lattice data 342
18.1 Lattice data 342
18.2 Numerical representation of the lattice structure 344
18.3 Spatial correlation 348
18.4 Modelling lattice data 352
18.5 More exotic models 355
18.6 Summary 359
19 Spatially continuous data analysis and modelling 361
19.1 Spatially continuous data 361
19.2 Geostatistical functions and assumptions 362
19.3 Exploratory variography analysis 366
19.4 Geostatistical modelling: Kriging 378
19.5 A full spatial analysis of the bird radar data 383
20 Univariate methods to analyse abundance of decapod larvae 393
20.1 Introduction 393
20.2 The data 394
20.3 Data exploration 397
20.4 Linear regression results 399
20.5 Additive modelling results 401
20.6 How many samples to take? 403
20.7 Discussion 405
21 Analysing presence and absence data for flatfish distribution in the Tagus estuary, Portugal 409
21.1 Introduction 409
21.2 Data and materials 410
21.3 Data exploration 412
21.4 Classification trees 415
21.5 Generalised additive modelling 417
21.6 Generalised linear modelling 418
21.7 Discussion 421
22 Crop pollination by honeybees in Argentina using additive mixed modelling 423
22.1 Introduction 423
22.2 Experimental setup 424
22.3 Abstracting the information 424
22.4 First steps of the analyses: Data exploration 427
22.5 Additive mixed modelling 428
22.6 Discussion and conclusions 434
23 Investigating the effects of rice farming on aquatic birds with mixed modelling 436
23.1 Introduction 436
23.2 The data 438
23.3 Getting familiar with the data: Exploration 439
23.4 Building a mixed model 443
23.5 The optimal model in terms of random components 446
23.6 Validating the optimal linear mixed model 449
23.7 More numerical output for the optimal model 450
23.8 Discussion 452
24 Classification trees and radar detection of birds for North Sea wind farms 454
24.1 Introduction 454
24.2 From radars to data 455
24.3 Classification trees 457
24.4 A tree for the birds 459
24.5 A tree for birds, clutter and more clutter 464
24.6 Discussion and conclusions 466
25 Fish stock identification through neural network analysis of parasite fauna 468
25.1 Introduction 468
25.2 Horse mackerel in the northeast Atlantic 469
25.3 Neural networks 471
25.4 Collection of data 474
25.5 Data exploration 475
25.6 Neural network results 476
25.7 Discussion 479
26 Monitoring for change: Using generalised least squares, non- metric multidimensional scaling, and the Mantel test on western Montana grasslands 482
26.1 Introduction 482
26.2 The data 483
26.3 Data exploration 486
26.4 Linear regression results 491
26.5 Generalised least squares results 495
26.6 Multivariate analysis results 498
26.7 Discussion 502
27 Univariate and multivariate analysis applied on a Dutch sandy beach community 504
27.1 Introduction 504
27.2 The variables 505
27.3 Analysing the data using univariate methods 506
27.4 Analysing the data using multivariate methods 513
27.5 Discussion and conclusions 518
28 Multivariate analyses of South-American zoobenthic species — spoilt for choice 521
28.1 Introduction and the underlying questions 521
28.2 Study site and sample collection 522
28.3 Data exploration 524
28.4 The Mantel test approach 527
28.5 The transformation plus RDA approach 530
28.6 Discussion and conclusions 530
29 Principal component analysis applied to harbour porpoise fatty acid data 532
29.1 Introduction 532
29.2 The data 532
29.3 Principal component analysis 534
29.4 Data exploration 535
29.5 Principal component analysis results 535
29.6 Simpler alternatives to PCA 541
29.7 Discussion 543
30 Multivariate analyses of morphometric turtle data — size and shape 545
30.1 Introduction 545
30.2 The turtle data 546
30.3 Data exploration 547
30.4 Overview of classic approaches related to PCA 550
30.5 Applying PCA to the original turtle data 552
30.6 Classic morphometric data analysis approaches 553
30.7 A geometric morphometric approach 558
31 Redundancy analysis and additive modelling applied on savanna tree data 563
31.1 Introduction 563
31.2 Study area 564
31.3 Methods 564
31.4 Results 567
31.5 Discussion 575
32 Canonical correspondence analysis of lowland pasture vegetation in the humid tropics of Mexico 577
32.1 Introduction 577
32.2 The study area 578
32.3 The data 579
32.4 Data exploration 581
32.5 Canonical correspondence analysis results 584
32.6 African star grass 587
32.7 Discussion and conclusion 589
33 Estimating common trends in Portuguese fisheries landings 591
33.1 Introduction 591
33.2 The time series data 592
33.3 MAFA and DFA 595
33.4 MAFA results 596
33.5 DFA results 598
33.6 Discussion 603
34 Common trends in demersal communities on the Newfoundland- Labrador Shelf 605
34.1 Introduction 605
34.2 Data 606
34.3 Time series analysis 607
34.4 Discussion 614
35 Sea level change and salt marshes in the Wadden Sea: A time series analysis 616
35.1 Interaction between hydrodynamical and biological factors 616
35.2 The data 618
35.3 Data exploration 620
35.4 Additive mixed modelling 622
35.5 Additive mixed modelling results 625
35.6 Discussion 628
36 Time series analysis of Hawaiian waterbirds 630
36.1 Introduction 630
36.2 Endangered Hawaiian waterbirds 631
36.3 Data exploration 632
36.4 Three ways to estimate trends 634
36.5 Additive mixed modelling 641
36.6 Sudden breakpoints 645
36.7 Discussion 646
37 Spatial modelling of forest community features in the Volzhsko- Kamsky reserve 647
37.1 Introduction 647
37.2 Study area 649
37.3 Data exploration 650
37.4 Models of boreality without spatial auto-correlation 652
37.5 Models of boreality with spatial auto-correlation 654
37.6 Conclusion 660
Index 681

Produkt-Details

• Erscheint lt. Verlag: 29.8.2007
• Reihe/Serie: Statistics for Biology and Health
• Reihe/Serie: Statistics for Biology and Health
• Zusatzinfo: XXVI, 672 p.
• Verlagsort: New York
• Sprache: englisch
• Themenwelt: Medizin / Pharmazie ► Allgemeines / Lexika
• Themenwelt: Studium ► 1. Studienabschnitt (Vorklinik) ► Biochemie / Molekularbiologie
• Themenwelt: Naturwissenschaften ► Biologie ► Ökologie / Naturschutz
• Themenwelt: Technik
• Schlagworte: Biology • classification • Data Analysis • Ecology • Fauna • linear regression • Statistics • Vegetation
• ISBN-10: 0-387-45972-3 / 0387459723
• ISBN-13: 978-0-387-45972-1 / 9780387459721