Applied Multivariate Statistics

Spring semester 2017

General information

Lecturer Fabio Sigrist
Assistants Samarth Shukla, Shu Li, Patricia Calvo Perez
Lectures Mon 8-10 HG E 5 >>
Exercises Mon 15-17 (every second week) HG E 1.2 >>
Course catalogue data >>

Course content

Multivariate statistics studies methods to analyze data on several random variables simultaneously. This course introduces the basic concepts and provides an overview of classical and modern methods of multivariate statistics, with an emphasis on applications and solving problems with the statistical software "R".

Announcements

  • Februar 3, 2017:
    Beginning of lecture: Monday, 20/02/2017 (Exercises start on 27/02/2017 at 15:15).

    Examples in the lecture and hints as well as solutions to the exercises will be based on the statistical software R. This is a freely available open source program that works on all platforms and has become worldwide standard for data analysis. It can be downloaded from CRAN. A R Tutorial can be found here.

    There will be a 120-minute written exam during the regular ETH exam sessions. The exam is a "closed book" exam, a simple pocket calculator with no communication capability is permitted. The exam covers all topics which were discussed and/or applied during either the lectures or the exercises. Upon passing the exam, the course will be awarded 5 ECTS credit points.

    PhD students who would like to obtain credit points but do not need to take the exam and obtain a grade need to sign up with the lecturer at the beginning of the semester and hand in 5 well-solved exercises.

Course materials

The schedule is subject to minor modifications. The slides will be uploaded before each lecture.

Week Topic
Week 1 Introduction & visualization
Week 2 Visualization & outliers
Week 3 Principal component analysis 1
Week 4 Principal component analysis 2
Week 5 Multidimensional scaling
Week 6 Factor analysis
Week 7 Cluster analysis
Week 8 Classification 1: discriminant analysis & logistic regression
Week 9 Extending univariate methods
Week 10 Classification 2: trees & random forest
Week 11 Models for repeated measures data
Week 12 Selection of additional machine learning methods

Literature:
Everitt and Hothorn (2011), An Introduction to Applied Multivariate Analysis with R, Springer
James, Witten, Hastie, and Tibshirani (2013), An Introduction to Statistical Learning, Springer
P. Dalgaard (2008), Introductory Statistics with R, Springer

Exercise classes

Exercise classes are held approx. every second week starting from 27/02/2017 in HG E 1.2. Please install R and RStudio and bring your laptop to the exercise classes, if possible.

Series and solutions

The series' solutions should be send to the assistants by email and by the due date. Please mark which part of your solutions are unclear and should be corrected.
There is no testat requirement.

Exercises Solutions Exercise/due date
Series 1 Solutions 1 27.2.17/6.3.17
Series 2 Solutions 2 13.3.17/20.3.17
Series 3 Solutions 3 27.3.17/3.4.17
Series 4 Solutions 4 10.4.17/19.4.17
Series 5 Solutions 5 15.5.17/22.5.17
Series 6 Solutions 6 29.5.17/5.6.17