Multivariate Statistics

Multivariate statistics covers a variety of topics falling mainly in two areas:  descriptive (clustering, principal components, correspondence analysis), and predictive (models with predictor variables and an outcome variable).  Various multivariate techniques constitute the core of what is used in research (especially models that explain relationships), and in data mining (prediction, classification, segmentation).

Here are the core courses in multivariate statistics at the Institute.  There are many others, especially in data mining, not listed here.

Matrix Algebra Review

Logistic Regression Multiple predictor variables, binary outcome

Advanced Logistic Regression

Multivariate Statistics General overview of multivariate data, plus focus on correspondence analysis and discriminant analysis

Generalized Linear Models General conceptual framework for linear models

Want to be notified of future courses?

Student comments