-

Multivariate Analysis for
Community Ecologists:
Step-by-Step using
PC-ORD

 -
Features
- Contents
Preface
Book Cover
Author
Errata
Purchase
Order Online
Mail or Fax Order Form
Software
Decision Tree Poster
Downloads
PC-ORD 6 Fixes
Data Set Example
Add-Ins
PC-ORD Demo
Support
FAQs
Network Installation
Discussion Group
Registration
Submit Suggestions
PC-ORD Training
Contact Us
Home
Multivariate Analysis for Community Ecologists:
Step-by-Step using PC-ORD

To order: In Canada or USA call 1-800-690-4499 or Order Online or Fax/Mail
Multivariate Analysis for Community Ecologists: Step-by-Step using PC-ORD Multivariate Analysis for Community Ecologists: Step-by-Step using PC-ORD
Multivariate Analysis for Community Ecologists: Step-by-Step using PC-ORD

Multivariate Analysis for Community Ecologists: Step-by-Step using PC-ORD is a book by
Dr. JeriLynn E Peck that answers your questions:

  • What are multivariate data?
  • How should I prepare my data?
  • Which analysis tools should I use?
  • What do they do?
  • Do they have weaknesses?
  • How do I interpret the output.

This richly illustrated book, published by MjM Software Design, 2010, will help you answer those questions by providing a step-by-step process for approaching your multivariate community data analysis project.  Simple explanations and diagrams explain the tools, recipes walk you though the process using the PC-ORD software, and guidance is given on everything from ensuring sampling independence to when to rotate an ordination.  Each technique has sections on:

  • what it's good for
  • what it actually does
  • what it means
  • what you need in order to run it
  • what you get in the output
  • what you should know about its strengths and weaknesses
  • how to run it in PC-ORD v.6
  • when you should use it

Contents
Preface i
Is this book for you? i
What's in this book i
How to use this book i
Why Multivariate? 1
The 10-Step Process 5
Step 1. Getting yourself ready 8
1. Univariate carryover 8
2. Define your analysis objective 14
Step 2. Getting your data ready 15
3. Matrix structures 15
4. Starting in PC-ORD 18
5. Inputting your data 22
Entering your data 22
Importing your data 23
From a spreadsheet 23
From a database 26
From a GIS 26
6. Screening your data 28
Screening with SUMMARY 28
Screening with SPECIES LISTS 29
Step 3. Structuring your data 30
7. Sampling adequacy 30
Is N enough? 30
Species Area Curves 30
8. Structuring your matrices 32
Restructuring with MODIFY DATA 32
Transposing matrices 32
Deleting rows 32
Deleting columns 33
Appending matrices 33
Random samples 34
Step 4. Exploring and preparing your data 35
9. What have you actually measured? 35
10. What do your zeros mean? 36
Dataset sparsity 36
Checking sparsity with SUMMARY 37
Checking sparsity with PROFILE 37
Reducing sparsity with DELETE COLUMNS 37
11. What do your non-zeros mean? 38
Response comparability 38
Standardizing with GENERAL RELATIVIZATION 39
Standardizing with RELATIVIZATION BY MAXIMUM 40
12. How variable are your data? 41
Uneven responses 41
Checking heterogeneity with SUMMARY 41
Checking heterogeneity with PROFILE 43
Outliers 43
Checking for outliers with SUMMARY 43
Checking for outliers with OUTLIER ANALYSIS 44
Checking for outliers with PROFILE 44
Checking for outliers with BOXPLOTS 44
Response distributions 44
Checking for normality with DISTRIBUTIONS 45
Checking for normality with BOXPLOTS 45
13. Selecting a distance measure 47
Euclidean distance 47
Chi-squared distance 48
City-block distance (e.g., Sørensen) 49
14. Tweaking to improve the signal 50
Improving statistical performance 50
Transforming to a POWER 50
Transforming to the LOGARITHMIC 50
Multiply or add a constant 51
15. Reweighting to match the objective 52
Whose story is it anyway? 52
Checking influence with DOMINANCE CURVES 52
Adjusting influence with RELATIVIZATIONS 52
Step 5: Selecting a model and tools 55
16. Selecting a model form 55
Hypothesizing underlying relationships 55
Exploring relationships with SCATTERPLOT 55
17. Selecting the tools 57
18. What is ordination? 59
Step 6a: Guiding pattern (guided ordination) 61
19. Weighted averaging (WA) 61
How to run it 62
20. Polar ordination (Bray-Curtis) 64
How to run it 66
21. Canonical correspondence analysis (CCA) 67
How to run it 72
22. Redundancy analysis (RDA) 74
How to run it 77
Step 6b: Looking for pattern (free ordination) 79
23. Principal components analysis (PCA) 79
How to run it 82
24. Nonmetric multidimensional scaling (NMS) 84
How to run it 88
Selecting dimensionality using the stress test 88
Verifying the final solution 89
NMS SCORES 91
Step 6c: Looking for groups (classification) 93
25. Cluster analysis 93
How to run it 97
Two-Way Cluster 98
Step 6d: Testing between and among groups 100
26. Multi-response permutation procedure (MRPP) 100
How to run it 118
27. Distance-based MANOVA (PerMANOVA) 103
How to run it 105
28. SumF 108
How to run it 109
29. Indicator species analysis (ISA) 110
How to run it 112
Blocked Indicator Species Analysis 113
30. Mantel test 114
How to run it 132
Partial Mantel Test 115
Step 7: Confirming your results 117
Step 8: Choosing what to share 118
Step 9: Interpreting what you found 119
31. Finding your story 119
Interpreting ordination diagrams 119
Overlay Main Matrix 120
Joint plots 121
Simple scatterplot 122
Overlay Second Matrix 123
% of variance 125
Successional vectors 125
Convex hulls and centroids 127
Interpreting randomization tests 128
Interpreting dendrograms 128
Interpreting ordered tables 130
Ordered main matrix 130
Two-way cluster dendrogram 131
TWINSPAN 131
Step 10: Presenting your story 133
32. Communicating your message 133
Presenting Summaries 133
Presenting Graphics 133
Rotating and reflecting ordinations 135
Drawing outlines on ordered tables 137
Appendix A: Notes 138
Appendix B: Check-list Template 139
Appendix C: Example Analysis Pathways 141
Appendix D: How to Report 155
Appendix E: Other PC-ORD Tools 157
Appendix F: Further Reading 159
Index 161