Graduate Courses

Multidimensional data; measures of location and variability and graphical data presentation. Random vectors and matrices, the concept of random sample, and the importance of statistical distance. Properties of the multivariate normal distribution. Random samples and parameter estimation for the multivariate normal distribution. Construction of confidence intervals and statistical hypothesis tests for the parameters of the multivariate normal distribution. One-way MANOVA for independent and dependent samples and related tests. Generalization of linear regression and its application to the interpretation and prediction of more than one dependent variable. Principal Component Analysis, determination of principal components from covariance and correlation matrices, sample principal components and statistical inference using large datasets. Correspondence Analysis and the study of contingency tables. Discriminant Analysis and Classification, study of group-separation rules, and hierarchical and non-hierarchical clustering methods.