1st Edition

# Essentials of Multivariate Data Analysis

By Neil H. Spencer Copyright 2014
186 Pages 38 B/W Illustrations
by Chapman & Hall

186 Pages
by Chapman & Hall

186 Pages
by Chapman & Hall

Also available as eBook on:

Since most datasets contain a number of variables, multivariate methods are helpful in answering a variety of research questions. Accessible to students and researchers without a substantial background in statistics or mathematics, Essentials of Multivariate Data Analysis explains the usefulness of multivariate methods in applied research.

Unlike most books on multivariate methods, this one makes straightforward analyses easy to perform for those who are unfamiliar with advanced mathematical formulae. An easily understood dataset is used throughout to illustrate the techniques. The accompanying add-in for Microsoft Excel® can be used to carry out the analyses in the text. The dataset and Excel add-in are available for download on the book’s CRC Press web page.

Providing a firm foundation in the most commonly used multivariate techniques, this text helps readers choose the appropriate method, learn how to apply it, and understand how to interpret the results. It prepares them for more complex analyses using software such as Minitab®, R, SAS, SPSS, and Stata.

What Questions?
What Analysis Should I Use?
What Data Do I Need?
What Data Is the Author Using in This Book?
What about Missing Data?
What about Other Topics?
What about Computer Packages?

Graphical Presentation of Multivariate Data
Why Do I Want to Do Graphical Presentations of Multivariate Data?
What Data Do I Need for Graphical Presentations of Multivariate Data?
The Rest of This Chapter
Comparable Histograms
A Step-by-Step Guide to Obtaining Comparable Histograms Using the Excel Add-In
Multiple Box Plots
A Step-by-Step Guide to Obtaining Multiple Box Plots Using the Excel Add-In
Trellis Plot
A Step-by-Step Guide to Obtaining a Trellis Plot using the Excel Add-In
Star Plots
Chernoff Faces
Andrews’ Plots
A Step-by-Step Guide to Obtaining Andrews’ Plots using the Excel Add-In
Principal Components Plot
A Step-by-Step Guide to Obtaining a Principal Components Plot Using the Excel Add-In

Multivariate Tests of Significance
Why Do I Want to Do Multivariate Tests of Significance?
What Data Do I Need for Multivariate Tests of Significance?
The Rest of This Chapter
Comparing Two Vectors of Means
Comparing Two Covariance Matrices
Comparing More than Two Vectors of Means
Comparing More than Two Covariance Matrices

Factor Analysis
Why Do I Want to Do Factor Analysis?
What Data Do I Need for Factor Analysis?
The Rest of This Chapter
How Do We Extract the Factors?
Interpreting the Results of a PCA Factor Analysis
How Many Factors Are There?
Interpreting the Results of a PAF Factor Analysis
Communalities Briefly Revisited
So Which Solution Do We Believe?
Factor Scores
A Step-by-Step Guide to Factor Analysis Using the Excel Add-In

Cluster Analysis
Why Do I Want to Do Cluster Analysis?
What Data Do I Need for Cluster Analysis?
The Rest of This Chapter
How Do We Decide How Close Together Two Cases Are?
How Do We Decide How Close Together Two Clusters Are?
How Do We Decide which Distance Measure and Linkage Method to Use?
How Do We Decide How Many Clusters There Are?
Interpreting Clusters
Non-Hierarchical Cluster Analysis
A Step-by-Step Guide to Cluster Analysis Using the Excel Add-In

Discriminant Analysis
Why Do I Want to Do Discriminant Analysis?
What Data Do I Need for Discriminant Analysis?
The Rest of This Chapter
How Do We Decide How Close a Case Is to Different Groups?
Allocating Individual Cases to Groups
Which Variables Discriminate between Groups?
How Accurate Are the Allocations?
Testing a Discriminant Analysis
Other Methods of Discriminant Analysis
A Step-by-Step Guide to Discriminant Analysis Using the Excel Add-In

Multidimensional Scaling
Why Do I Want to Do Multidimensional Scaling?
What Data Do I Need for Multidimensional Scaling?
The Rest of This Chapter
Classical Multidimensional Scaling
Other Methods of Multidimensional Scaling
A Step-by-Step Guide to Multidimensional Scaling Using the Excel Add-In

Correspondence Analysis
Why Do I Want to Do Correspondence Analysis?
What Data Do I Need for Correspondence Analysis?
The Rest of This Chapter
Chi-Square Distances, Inertia and Plots
More Dimensions
Row, Column and Symmetric Normalisations
Correspondence Analysis with More than Two Variables
A Step-by-Step Guide to Correspondence Analysis Using the Excel Add-In

References

Index

### Biography

Dr. Neil H. Spencer is a reader in applied statistics and director of the Statistical Services and Consultancy Unit at the University of Hertfordshire. His research interests include multilevel models, multivariate methods, statistical computing, multiple testing, and testing for randomness.

"Postgraduate students without a mathematical or statistical background may find the book helpful as a first step in investigating which multivariate statistics technique may be appropriate to use in their research. … the writing style is very conversational and the mathematics is kept to a minimum. … This book could also be used in an undergraduate research methods course in the social sciences or any other area where the students have a reputation of fearing mathematics."
Australian & New Zealand Journal of Statistics, 2016

"… this text provides an overview at an introductory level of several methods in multivariate data analysis. It contains in-depth examples from one data set woven throughout the text, and a free [Excel] Add-In to perform the analyses in Excel, with step-by-step instructions provided for each technique. … could be used as a text (possibly supplemental) for courses in other fields where researchers wish to apply these methods without delving too deeply into the underlying statistics."
The American Statistician, February 2015

"… a good introductory read for students studying more mathematical/statistical courses …"
International Journal of Environmental Analytical Chemistry, 2015