Duration
10h Th, 10h Pr
Number of credits
| Master in biology of organisms and ecology (120 ECTS) | 2 crédits |
Lecturer
Language(s) of instruction
French language
Organisation and examination
Teaching in the first semester, review in January
Units courses prerequisite and corequisite
Prerequisite or corequisite units are presented within each program
Learning unit contents
The course is a general introduction to the methods used in multivariate statistics, i.e. when one studies several variables simultaneously. The course entails the following chapters:
- Graphical display of multivariate data
- Multivariate tests
- Multivariate exploratory techniques: principal component analysis, clustering, principal coordinates analysis
- Discriminant analysis
- Multiple regression and generalized linear models
Learning outcomes of the learning unit
The methods of multivariate data analysis are taught based on a pragmatic approach. At the end of the course, the sudent should be capable of
- defining a multivariate problem,
- analysing the data,
- interpreting the results.
He/she should also be aware of the limitations of application of the methods.
Prerequisite knowledge and skills
The students must have attended a basic course on descriptive and inferential statistics. The concepts of normal distribution, confidence interval and hypothesis tests are considered as known. Moreover, basic knowledge of the software R is expected.
The methods are presented without emphasizing the mathematical justifications. Nevertheless, the students must have the following background in mathematics: basic linear algebra (vectors, matrices, including the notions of determinant and inverses), linear, exponential and logarithmic functions.
Planned learning activities and teaching methods
Together with the ex-cathedra courses focusing on a theoretical approach, the students will be asked to apply the techniques following the learning process describred below:
- Personal preparation at home in order to get familiar with the script constructed by the professor and her assistants;
- Discussion on the script and the interpretation of the resultats in the computer room of the maths department;
- Personal homework (data analyses to perfom by oneself; corrections are provided later on in order to provide a self assesment)
Mode of delivery (face-to-face ; distance-learning)
The course counts 20 hours of face-to-face teaching. Each lecture lasts 2h30 and is decomposed into two parts: theory (ex-cathedra) and a practical in a computer room. The data analyses that cannot be finished during the practical have to be completed at home by the student.
Recommended or required readings
There are no lecture notes but the slides that will be used for the lectures will be available on eCampus in advance. Also, the scripts of the software R and the exercises sheets (and their corrections) will be displayed on line following the evolution of the lectures.
Textbooks are:
- Multivariate statistical methods. D. Morrison, Mc Graw-Hill, Auckland, 1986
- Introduction to multivariate analysis. C. Chatfield et A.J. Collins, Chapman and Hall. ed, London, 1980
Assessment methods and criteria
Written examination in the computer room.
Work placement(s)
Organizational remarks
The course will take place on Tuesday morning of the fisrt quadrimester in Building B37.
Contacts
Lecturer
Gentiane Haesbroeck
Département de Mathématique (B37, bureau 0/60)
Tél: 04/366.95.94
Email: G. Haesbroeck@ulg.ac.be
Assistant
Marie Ernst
Tél: 04/366. 366.94.02
Email: m.ernst@ulg.ac.be