Advanced Multivariate Statistics

A.Y. 2022/2023
6
Max ECTS
40
Overall hours
SSD
SECS-S/01
Language
English
Learning objectives
This course is divided in two parts: (i) inference for multivariate analysis and (ii) exploratory multivariate analysis. The first part takes up the concepts of inferential multivariate statistical analysis, extending the theory about univariate inferential statistics with all the implications this extension involves. Additional topics in this context are Bayesian networks and multivariate bootstrapping. The second part will focus on exploratory multivariate analysis and will focus on further dimensional reduction techniques, correlation analysis and advanced clustering. During the course, applications to real situations will be presented using mainly the R statistical package.
Expected learning outcomes
Students will achieve skills for doing independent study and research in presence of multivariate data. Moreover, they will learn how to use dedicated R libraries to deal with multivariate contexts.
Single course

This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.

Course syllabus and organization

Single session

Lesson period
First trimester
Teaching methods.
Classes will be held on the Microsoft Teams platform both in synchronous (i.e. live) and asynchronous (i.e. recorded) mode.
Course syllabus
First part: multivariate inference
(i) Multivariate normal distributions.
(ii) Multivariate analysis of variance.
(iii) Log-linear and logistic models for categorical multivariate data.
(iv) Models for multivariate response variables
(v) Multivariate bootstrapping.
(vi) Robust multivariate analysis
(vii) Bayesian networks
Second part: exploratory multivariate data analysis
(i) Nonlinear principal component analysis
(ii) Multidimensional scaling
(iii) Multiple correspondance analysis
(iv) Canonical correlation
(v) Advanced cluster analysis
Prerequisites for admission
No compulsory prerequisites are required, but a good knowledge of basic statistics and probability is strongly recommended. Matrix algebra and calculus will be beneficial but are not strictly required. Basic programming skills (especially in R) are also useful.
Teaching methods
60% lecture-style classes;
40% classroom interactive teaching activities focused on examples, case studies, research papers and applications developed mainly in R.
Teaching Resources
Lecture notes and slides from the course.
Suggested reading for insights on some topics:
Everitt, B.S., Hothorn, T. (2011). An Introduction to Applied Multivariate Analysis with R. Springer.
Everitt, B.S., Dunn, G. (2017). Applied Multivariate Data Analysis, 2nd edition. Springer.
Gifi, A. (1990). Nonlinear Multivariate Analysis. Wiley.
Härdle, W., Simar, L. ( 2007). Applied Multivariate Statistical Analysis, 2nd edition . Springer.
Bouveyron, C., Celeux, G., Murphy, T.B., Raftery, A., E. (2019). Model-based Clustering and Classification for Data Science. Springer
Assessment methods and Criteria
Some assignments will be delivered and evaluated during the course and a written final project is required. Evaluation of the project will be performed through an oral presentation and examination, in which students will be asked questions about the methods used in the project, the code produced and on topics from the rest of the syllabus.
SECS-S/01 - STATISTICS - University credits: 6
Lessons: 40 hours
Professor: Manzi Giancarlo