## Multivariate Statistical Methods: A Primer, Third EditionMultivariate methods are now widely used in the quantitative sciences as well as in statistics because of the ready availability of computer packages for performing the calculations. While access to suitable computer software is essential to using multivariate methods, using the software still requires a working knowledge of these methods and how they can be used. Multivariate Statistical Methods: A Primer, Third Edition introduces these methods and provides a general overview of the techniques without overwhelming you with comprehensive details. This thoroughly revised, updated edition of a best-selling introductory text retains the author's trademark clear, concise style but includes a range of new material, new exercises, and supporting materials on the Web. New in the Third Edition: In his efforts to produce a book that is as short as possible and that enables you to begin to use multivariate methods in an intelligent manner, the author has produced a succinct and handy reference. With updated information on multivariate analyses, new examples using the latest software, and updated references, this book provides a timely introduction to useful tools for statistical analysis. |

### What people are saying - Write a review

User Review - Flag as inappropriate

This book is as the title states: a primer on multivariate statistics. The coverage is good with enough details to understand the different methods. There isn't much hard-core theory.

### Contents

The material of multivariate analysis | vii |

12 Preview of multivariate methods | 12 |

13 The multivariate normal distribution | 14 |

14 Computer programs | 15 |

16 Chapter summary | 16 |

Matrix algebra | 17 |

23 Operations on matrices | 19 |

24 Matrix inversion | 21 |

Exercise | 103 |

Discriminant function analysis | 105 |

83 Canonical discriminant functions | 107 |

84 Tests of significance | 108 |

85 Assumptions | 109 |

86 Allowing for prior probabilities of group membership | 114 |

88 Jackknife classification of individuals | 116 |

810 Logistic regression | 117 |

25 Quadratic forms | 22 |

27 Vectors of means and covariance matrices | 23 |

28 Further reading | 25 |

References | 26 |

Displaying multivariate data | 27 |

33 The draftsmans plot | 29 |

34 The representation of individual data points | 30 |

35 Profiles of variables | 32 |

36 Discussion and further reading | 33 |

37 Chapter summary | 34 |

Tests of significance with multivariate data | 35 |

the multivariate case | 37 |

44 Multivariate versus univariate tests | 41 |

the singlevariable case | 42 |

47 Comparison of means for several samples | 46 |

48 Comparison of variation for several samples | 49 |

49 Computer programs | 54 |

Exercise | 55 |

References | 57 |

Measuring and testing multivariate distances | 59 |

53 Distances between populations and samples | 62 |

54 Distances based on proportions | 67 |

55 Presence absence data | 68 |

56 The Mantel randomization test | 69 |

57 Computer programs | 72 |

59 Chapter summary | 73 |

Exercise | 74 |

Principal components analysis | 75 |

62 Procedure for a principal components analysis | 76 |

63 Computer programs | 84 |

64 Further reading | 85 |

Exercises | 87 |

References | 90 |

Factor analysis | 91 |

72 Procedure for a factor analysis | 93 |

73 Principal components factor analysis | 95 |

74 Using a factor analysis program to do principal components analysis | 97 |

75 Options in analyses | 100 |

76 The value of factor analysis | 101 |

78 Discussion and further reading | 102 |

811 Computer programs | 122 |

813 Chapter summary | 123 |

Exercises | 124 |

Cluster analysis | 125 |

93 Hierarchic methods | 127 |

94 Problems of cluster analysis | 129 |

96 Principal components analysis with cluster analysis | 130 |

97 Computer programs | 134 |

98 Discussion and further reading | 135 |

99 Chapter summary | 136 |

Exercises | 137 |

References | 141 |

Canonical correlation analysis | 143 |

102 Procedure for a canonical correlation analysis | 145 |

103 Tests of significance | 146 |

104 Interpreting canonical variates | 148 |

105 Computer programs | 158 |

107 Chapter summary | 159 |

References | 161 |

Multidimensional scaling | 163 |

112 Procedure for multidimensional scaling | 165 |

113 Computer programs | 172 |

114 Further reading | 174 |

Exercise | 175 |

Ordination | 177 |

122 Principal components analysis | 178 |

123 Principal coordinates analysis | 181 |

124 Multidimensional scaling | 189 |

125 Correspondence analysis | 191 |

126 Comparison of ordination methods | 196 |

127 Computer programs | 197 |

129 Chapter summary | 198 |

Epilogue | 201 |

133 Missing values | 202 |

References | 203 |

Computer packages for multivariate analyses | 205 |

References | 207 |

209 | |

211 | |

### Other editions - View all

### Common terms and phrases

alar extent Bannadi birds body measurements calculated canine groups canonical correlation analysis canonical variables Chapter summary chi-squared cluster analysis coefficients colonies column comparison Computer programs considered correlation matrix correspondence analysis Cuon data in Table described dimensions discriminant function analysis discussed Egyptian skulls eigenvalues eigenvectors Equation estimated Euclidean distance example F-test factor analysis further reading Golden jackal Indian wolf indices individual linear combinations logistic regression Mahalanobis distance mandible measurements matrix algebra mean values mean vectors Modern dog molar multidimensional scaling multivariate analysis multivariate data multivariate normal distribution nonmetric objects observations ooooooooooooooooooooooooooooooo options ordination original variables percentages plot population mean possible Prehistoric dog principal components analysis principal coordinates analysis problem random relationship rotation sample mean shown in Table shows significant result significantly large similarity matrix standard deviation statistical packages Steneryd Nature Reserve survivors and nonsurvivors Thai dogs tions uncorrelated variation