Laurea Magistrale (M.Sc.) in Stochastics and Data Science

Multivariate statistical analysis

Multivariate statistical analysis

Academic year 2017/2018

Sommario del corso

• Course objectives
• Results of learning outcomes
• Course delivery
• Learning assessment methods
• Program
• Suggested textbooks and readings
• Teaching tools

Course objectives

Results of learning outcomes

The student will learn the basic techniques for analyzing multi-dimensional data (including visualization), study multivariate distributions and their properties, discuss various methods for dimension reduction.

Course delivery

The course is composed of 48 hours of class lectures. Examples and exercises will be dealt with at class through the R language.

Learning assessment methods

Problem Sets:
There will be 2 problem sets assigned throughout the course.  They will be posted in due time on
https://sites.google.com/a/carloalberto.org/pdeblasi/teaching
together with an indication of the deadline.
Problem sets must be submitted and there are no late submissions. They are an essential part of the course, providing students with a guide on how well they are grasping the material on a "real time" basis. They request the solution of exercises, solution which might require the use of a statistical software. Students are encouraged to work in groups on the problem sets. However, students should understand the material on their own, and hand in their own problem sets.

Exam:
There will be a final exam, check out for dates on
http://www.master-sds.unito.it
The final examination consists of a written test, either a short or a long test according to the problem sets. Specifically,

(1) First 2 exam dates: the course grade is determined by the problem sets and the final exam. The final exam consists of a short written test (1h) on the part of the program not covered by problem sets followed by an oral examination. The final grade will be a combination of the problem sets grades (66%),  and the final exam grade (33%).  For students who have failed to submit the solutions of the problem sets, case (2) below applies.

(2) From the 3rd exam date on: the final exam consists of a long written test (3h) on the whole program and the final grade will be determined solely by it (100%).

Program

- Introduction
       - summary statistics for multivariate data
       - multivariate data visualization
       - multivariate Gaussian distributions
- Principal Component Analysis (PCA):
       - geometric and algebraic basics of PCA
       - calculation and choice of components
       - plotting PCs, interpretation
- Factor Analysis (FA):
       - model definition and assumptions
       - estimation of loadings and communalities
       - choice of the number of factors
       - factor rotation
- Canonical Correlation Analysis:
       - computation and interpretation
       - relationship with multiple regression
- Discriminant Analysis and Classification:
       - classification rules
       - linear and quadratic discrimination
       - error rates
- Cluster Analysis:
       - measure of similarity
       - hierarchical clustering
       - K-means clustering
       - model based clustering

The bibliography, to be confirmed at the beginning of the course, is:

- R.A. Johnson and D.W. Wichern (2007). Applied Multivariate Statistical Analysis. Prentice-Hall, 6th Ed.

Suggested readings:
- Hastie, Tibshirani, Friedman (2009). The Elements of Statistical Learning, 2nd ed., Springer
- Afifi A., May S., Clark V.A. (2012). Practical Multivariate Analysis, 5th ed., Chapman & Hall/CRC
- Everitt B. (2005). An R and S-PLUS Companion to Multivariate Analysis. Springer
- Rencher A. C., Christensen W. F. (2012). Methods of multivariate analysis, 3rd ed., Wiley
- Rencher A.C. (1992). Interpretation of canonical discriminant functions, canonical variates and principal components. The American Statistician 46, 217-225.

Class schedule

• Teaching materials
• Exams and finals
• Go to Moodle
• Visit the forums