product iamge

Exploratory Multivariate Analysis by Example Using R

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

Full of real-world case studies and practical advice, Exploratory Multivariate Analysis by Example Using R focuses on four fundamental methods of multivariate exploratory data analysis that are most suitable for applications. It covers principal component analysis (PCA) when variables are quantitative, correspondence analysis (CA) and multiple correspondence analysis (MCA) when variables are categorical, and hierarchical cluster analysis.

The authors take a geometric point of view that provides a unified vision for exploring multivariate data tables. Within this framework, they present the principles, indicators, and ways of representing and visualizing objects that are common to the exploratory methods. The authors show how to use categorical variables in a PCA context in which variables are quantitative, how to handle more than two categorical variables in a CA context in which there are originally two variables, and how to add quantitative variables in an MCA context in which variables are categorical. They also illustrate the methods and the ways they can be exploited using examples from various fields.

Throughout the text, each result correlates with an R command accessible in the FactoMineR package developed by the authors. All of the data sets and code are available at http://factominer.free.fr/book

By using the theory, examples, and software presented in this book, readers will be fully equipped to tackle real-life multivariate data.

Author(s): Francois Husson, Sebastien Le, Jerome Pages
Series: Chapman & Hall/CRC Computer Science & Data Analysis
Edition: 1
Publisher: CRC Press
Year: 2010

Language: English
Pages: 240

b10345-1.pdf......Page 1
Contents......Page 5
Preface......Page 11
1.2 Objectives......Page 13
1.2.1 Studying Individuals......Page 14
1.2.2 Studying Variables......Page 15
1.3.1 The Cloud of Individuals......Page 17
1.3.2 Fitting the Cloud of Individuals......Page 19
1.3.3 Representation of the Variables as an Aid for Interpreting the Cloud of Individuals......Page 23
1.4.1 The Cloud of Variables......Page 25
1.4.2 Fitting the Cloud of Variables......Page 26
1.5 Relationships between the Two Representations NI and NK......Page 28
1.6.1 Numerical Indicators......Page 29
1.6.2 Supplementary Elements......Page 32
1.6.3 Automatic Description of the Components......Page 36
1.7 Implementation with FactoMineR......Page 37
1.8.1 Testing the Significance of the Components......Page 38
1.8.3 Simultaneous Representation: Biplots......Page 39
1.8.6 Varimax Rotation......Page 40
1.9.1 Data Description — Issues......Page 41
1.9.3 Implementation of the Analysis......Page 43
1.10.2 Analysis Parameters......Page 56
1.10.3 Implementation of the Analysis......Page 58
1.11.1 Data Description — Issues......Page 63
1.11.3 Implementation of the Analysis......Page 64
2.1 Data — Notation — Examples......Page 71
2.2.1 Objectives......Page 73
2.2.2 Independence Model and X2 Test......Page 74
2.2.3 The Independence Model and CA......Page 76
2.3.1 Clouds of Row Profiles......Page 77
2.3.2 Clouds of Column Profiles......Page 78
2.3.3 Fitting Clouds NI and NJ......Page 80
2.3.4 Example: Women's Attitudes to Women's Work in France in 1970......Page 81
2.3.5 Superimposed Representation of Both Rows and Columns......Page 84
2.4.1 Inertias Associated with the Dimensions (Eigenvalues)......Page 89
2.4.2 Contribution of Points to a Dimension's Inertia......Page 92
2.4.3 Representation Quality of Points on a Dimension or Plane......Page 93
2.4.4 Distance and Inertia in the Initial Space......Page 94
2.5 Supplementary Elements (= Illustrative)......Page 95
2.6 Implementation with FactoMineR......Page 98
2.7 CA and Textual Data Processing......Page 100
2.8.1 Data Description — Issues......Page 104
2.8.2 Implementation of the Analysis......Page 106
2.9.1 Data Description — Issues......Page 113
2.9.3 Inertia......Page 116
2.9.4 Representation on the First Plane......Page 118
2.10.1 Data Description — Issues......Page 121
2.10.2 Margins......Page 123
2.10.3 Inertia......Page 124
2.10.4 First Dimension......Page 127
2.10.5 Plane 2-3......Page 129
2.10.6 Projecting the Supplementary Elements......Page 133
2.10.7 Conclusion......Page 137
3.1 Data — Notation — Examples......Page 139
3.2.1 Studying Individuals......Page 140
3.2.2 Studying the Variables and Categories......Page 141
3.3.2 Distances between the Categories......Page 142
3.4.1 Relationship between MCA and CA......Page 144
3.4.2 The Cloud of Individuals......Page 145
3.4.3 The Cloud of Variables......Page 146
3.4.4 The Cloud of Categories......Page 147
3.4.5 Transition Relations......Page 150
3.5.1 Numerical Indicators......Page 152
3.5.2 Supplementary Elements......Page 154
3.5.3 Automatic Description of the Components......Page 155
3.6 Implementation with FactoMineR......Page 157
3.7.1 Analysing a Survey......Page 160
3.7.2 Description of a Categorical Variable or a Subpopulation......Page 162
3.7.3 The Burt Table......Page 166
3.8.1 Data Description — Issues......Page 167
3.8.2 Analysis Parameters and Implementation with FactoMineR......Page 170
3.8.3 Analysing the First Plane......Page 171
3.8.4 Projection of Supplementary Variables......Page 172
3.9.1 Data Description — Issues......Page 174
3.9.3 Representation of Individuals on the First Plane......Page 176
3.9.4 Representation of Categories......Page 177
3.9.5 Representation of the Variables......Page 178
4.1 Data — Issues......Page 180
4.2.1 Similarity between Individuals......Page 184
4.2.2 Similarity between Groups of Individuals......Page 187
4.3.1 Classic Agglomerative Algorithm......Page 188
4.4 Ward's Method......Page 190
4.4.1 Partition Quality......Page 191
4.4.2 Agglomeration According to Inertia......Page 192
4.4.3 Two Properties of the Agglomeration Criterion......Page 194
4.4.4 Analysing Hierarchies, Choosing Partitions......Page 195
4.5.1 Data — Issues......Page 196
4.5.2 Principle......Page 197
4.5.3 Methodology......Page 198
4.6 Partitioning and Hierarchical Clustering......Page 0
4.7 Clustering and Principal Component Methods......Page 199
4.7.2 Simultaneous Analysis of a Principal Component Map and Hierarchy......Page 200
4.8.2 Analysis Parameters......Page 201
4.8.3 Implementation of the Analysis......Page 202
4.9.2 Constructing the AHC......Page 208
4.9.3 Defining the Clusters......Page 210
4.10 Dividing Quantitative Variables into Classes......Page 213
A.1 Percentage of Inertia Explained by the First Component or by the First Plane......Page 216
A.2.1 Introduction......Page 221
A.2.2 The Rcmdr Package......Page 225
A.2.3 The FactoMineR Package......Page 227
Bibliography of Software Packages......Page 232
Bibliography......Page 234