Skip to content

Latest commit

 

History

History
12 lines (10 loc) · 1.29 KB

File metadata and controls

12 lines (10 loc) · 1.29 KB

STAT_32950

Various computational assignments from STAT 32950 (Multivariate Statistical Analysis), taught by Dr. Mei Wang, at UChicago.

  • In Homework 0, we review the basics of formatting equations with LaTeX and plotting using base R.
  • In Homework 1, we compare and contrast various measures of correlation (including Pearson's r, Kendall tau, and Spearman's rho) and examine the eigenvectors and eigenvalues of the correlation matrix.
  • In Homework 2, we study principal component analysis (PCA) and factor analysis.
  • In Homework 3, we study canonical correlation analysis (CCA) and Hotelling's T^2 statistic.
  • In Homework 4, we study MANOVA, various approaches to constructing confidence intervals in the multidimensional setting, multidimensional scaling (MDS), and correspondence analysis (CA).
  • In Homework 5, we study supervised learning methods, including k-Nearest Neighbors (kNN), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machines (SVM).
  • In Homework 6, we study unsupervised learning methods, including k-means clustering, hierarchical clustering, and mixture models.
  • In Homework 7, we compare and contrast regularization methods including ridge, LASSO, and elastic nets; we also contrast PCA with sparse PCA and independent component analysis (ICA).