Multivariate Analysis

Multivariate normal distribution, estimation and hypothesis testing for the multivariate normal distribution, multivariate linear regression, prinsipal components, factor analysis, disciminant analysis, classification and cluster analysis.

The course gives a theoretical introduction to statistical methods for multivariate data (i.e. several variables are measured for each observational unit, and we are interested in using all the variables and their correlation). The students shall be capable of conducting simple statistical analyses of multivariate data using the programming package R.

Ledtures, exercises, project/term paper. The exercises demand the use of a computer (computing programme R). The lectures may be given in English. Portfolio assessment is the basis for the grade awarded in the course. This portfolio comprises a written final examination 80% and the semester assignment 20%. The results for the constituent parts are to be given in %-points, while the grade for the whole portfolio (course grade) is given by the letter grading system. Retake of examination may be given as an oral examination.