Project Details

Project Title: Multivariate Statistics: Old School (MSOS)

Project URL: http://cran.r-project.org/web/packages/msos/

Code Repository: https://github.com/coatless/msos

Project Version: 1.1.0

Project Status: Maintenance releases

Project Description: R Package implementation of R functions and data sets used in John Marden’s Multivariate Statistics Old School textbook. The package contains detailed documentation of the functions and datasets. This includes a slew of examples to understand functions.

The package features:

  • Both Sides Models
    • Least Squares
    • MLE
    • LRT, $\chi ^2$, and hotelling Tests on subsets of $\beta$
    • Degrees of Freedom
  • Maximizing negentropy for $Q = 1, 2, 3$ dimensions.
  • BIC from a set of observed eigenvalues given a specific pattern.
  • Quadratic discrimination (QDA) calculation and prediction
  • Linear Discrimination (LDA) calculation
  • Silhouettes for K-Means Clustering
  • Many unique data sets
    • births, caffeine, cars, cereal, crabs, decathlon08, decathlon12, election, exams, grades, histamine, leprosy, mouths, painters, planets, prostaglandin, SAheart, skulls, softdrinks, Spam, sportsranks, states
  • Features R should have but does not: logdet, trace (tr), imax (largest value index), fillout (transform matrix to square), reverse.kronecker