Familiarity with the basic statistical tools necessary for summarising univariate or bivariate data sets.
The aim of the course is to provide students with skills necessary to analyse multivariate data sets by selecting the suitable statistical technique in a given experimental situation and by drawing meaningful conclusions from the analysis. Moreover, at the end of module, the student will be expected to be sufficiently familiar with the basic definitions and rules of matrix algebra which are necessary to understand multivariate methods for data analysis.
Data matrix. Relations between quantitative variables: covariance matrix and correlation matrix. Measure of multidimensional variability.
Graphics of multivariate data.
Distances and similarity indices.
Multivariate data analysis methods with particular emphasis to principal component analysis, correspondence analysis, cluster analysis.
Barabesi L., Fattorini L. (2010) Introduzione all’algebra delle matrici, Giuffrè Editore.
Zani S., Cerioli A. (2007) Analisi dei dati e data mining per le decisioni aziendali, Giuffrè Editore.
- Partial examination: Written examination.
- Final examination: both a written and an oral examination.