Class 1 (Module III)

16 Maio 2022, 09:30 • Jorge Filipe Campinos Landerset Cadima

[Slides PCA+LDA 1-50] Introduction to Multivariate Analysis: programme, bibliography, a few introductory remarks. Some essential matrix concepts: orthogonal matrices; trace of a square matrix and its properties, eigenvalues and eigenvectors. A fundamental result: the Spectral Decomposition of symmetric matrices. A statistical approach to Principal Component Analysis. The goal, the formulation of the problem and its solution via the Rayleigh-Ritz Theorem. Properties of principal components. PCA with R: the prcomp command. An example with the crayfish (lavagantes) dataset. The dependence of PCA on the units of measurement. PCA on the standardised data (correlation matrix PCA): concept and discussion. Again the crayfish example.
Nota: Esta aula foi leccionada na quarta-feira, dia 25.5.22, simultaneamente presencial e por zoom. Devido a um problema de conexão à rede, acabou por ser leccionada na Sala S1, das 15h30 às 18h00,