Multivariate Statistics: Old School is a
mathematical and methodological introduction to multivariate statistical analysis.
It presents the basic mathematical grounding that graduate statistics students need for future research, and
important multivariate techniques useful to statisticians in general.
This text was developed over many years by the author,
while teaching in the Department of Statistics, University of Illinois
The multivariate normal and Wishart distributions
Linear models, including multivariate regression and analysis of variance, and
both-sides models (GMANOVA, repeated measures, growth curves)
Linear algebra useful for multivariate statistics
Covariance structures, including principal components,
factor analysis, independence and conditional independence, and symmetry models
Classification (linear and quadratic discrimination, trees, logistic regression)
Clustering (K-means, model-based, hierarchical)
Other techniques, including biplots, canonical correlations, and multidimensional scaling
The Data Program has facilities for displaying interactive point clouds,
including calculation of some marginal projection pursuit quantities (variance, skewness, kurtosis, negentropy).
The data for Exercises 1.9.23 through 1.9.28 in the book can be found in the "Spin Examples" collection of data sets in the
Data Program. More info on using the program.
Home: Stat.Istics.Net — Bringing statistics into the 20th century
Data Program: Analyze data — Histograms, scatter plots, multiple regression, chi-square tests of independence, logistic regression.
Box models: Randomly draws tickets from a box, to see the law of averages and the central limit theorem.