The courses gives an introduction to multivariate statistical analysis. The focus of the course is on the following techniques for quantitative variables: principal component analysis, correspondence analysis and cluster analysis. Examples and case studies will illustrate usage and results interpretation. The empirical analysis will be conducted using appropriate statistical software (SAS, STATA, R).
Zani S. e Cerioli A. (2007) Analisi dei dati e data mining per le decisioni aziendali, Milano: Giuffrè.
Johnson R.A. e Wichern D.W. (2007). Applied Multivariate Statistical Analysis. Sixth Edition. Pearson Education International.
Learning Objectives
Introduction to multivariate statistical techniques for the joint analysis of two or more variables: data reduction techniques, relationships among variables, similarity and dissimilarity measures.
Prerequisites
Linear algebra, descriptive statistics.
Further information
Course material available on the e-learning platform of the University of Florence: http://e-l.unifi.it
Type of Assessment
Practical examination
Course program
Detailed list of arguments:
- Introduction to multivariate analysis. Data matrix and scales of measurements.
- Covariance and correlation matrices..
- Principal component analysis
- Correspondence analysis
- Distance and similarity measures
- Cluster analysis
Theoretical lessons will be complemented by lab sessions, using X SAS. Students will be asked to do individual homeworks.