
Dr. Richard J. Harris University of New Mexico
Drawing upon over 30 years of experience in working with statistics, Dr. Richard J. Harris has updated A Primer of Multivariate Statistics to provide a model of balance between how-to and why. This classic text covers multivariate techniques with a taste of latent variable approaches. New Features include:
- many more effective examples;
- infusions of humor throughout the text;
- coverage of path analysis and structural equation modeling;
- computer applications throughout the text;
- a more detailed discussion of how to construct and interpret linear combinations of sets of independent and dependent variables;
- coverage of recent developments in univariate statistics: the proposed ban on null hypothesis significance testing (NHST) and the use of three-alternative hypothesis-testing logic as the antidote for NHST's proposed ill's, two simple alternatives to power calculations to determine sample size, and a confidence-interval (CI) procedure that is appropriate when using split-tailed tests and that, if one's a priori predictions of effect size are right, yields narrower CIs than traditional procedures;
- unique discussion of the distinction between rotations of principal components that keep the rotated principal components mutually uncorrelated and those that keep the profiles of scores that define them mutually orthogonal;
- expanded coverage of confirmatory factor analysis.
This edition retains its conversational writing style while focusing on classical techniques. The book gives the reader a feel for why one should consider diving into more detailed treatments of computer-modeling and latent-variable techniques, such as non-recursive path analysis, confirmatory factor analysis, and hierarchical linear modeling. Throughout the book there is a focus on the importance of describing and testing one's interpretations of the emergent variables that are produced by multivariate analysis.
"The coverage of the book is essentially classical multivariate statistics, based on the normal distribution, plus a discussion of factor analysis. This, I think, is a good choice, and fits well with Harris' goal to make the book a primer that presents the concepts a researcher needs to make good use of the computer packages." -- Thomas D. WickensUniversity of California at Los Angeles
Contents
- Preface.
- The Forest Before the Trees.
- Multiple Regression: Predicting One Variable From Many.
- Hotelling's T2: Tests on One or Two Mean Vectors.
- Multivariate Analysis of Variance: Differences Among Several Groups on Several Measures.
- Canonical Correlation: Relationships Between Two Sets of Variables.
- Principal Component Analysis: Relationships Within a Single Set of Variables.
- Factor Analysis: The Search for Structure.
- The Forest Revisited.
- Digression 1: Finding Maxima and Minima of Polynomials.
- Digression 2: Matrix Algebra.
- Digression 3: Solution of Cubic Equations.
- Appendices:
- Statistical Tables.
- Computer Programs Available From the Author.
- Derivations.
[此贴子已经被作者于2005-8-22 10:20:52编辑过]