30705 - Data Analysis

Learning outcomes

By the end of the course the student gains an appreciation of the types of problems and questions which arise with multivariate data. In particular the student should be able: - to apply and interpret methods of dimension reduction (including principal component analysis and factor analysis); - to apply and interpret methods for cluster analysis and discrimination; - to interpret the output of R procedures for multivariate statistics.

Course contents

Principal component analysis -  Geometrical concepts. Mathematical details. Properties and practical considerations. Principal component analysis in regression.

Factor analysis  - The linear factor model: specification, identification, estimation.

Cluster analysis -  Distances and dissimilarities. Hierarchical clustering methods. K-means clustering.

Discriminant analysis - Discrimination when the populations are known  (maximum likelihood and bayes discriminant rules). Discrimination under estimation. Fisher's linear discriminant function. Probabilities of misclassification.

Readings/Bibliography

S. Mignani, A. Montanari, Appunti di analisi statistica multivariata, Esculapio, Bologna, 1994.

W.J. Krzanowski, Principles of Multivariate Analysis: A User's Perspective, 1988, Oxford University Press.

Teaching methods

Lectures and practicals

Assessment methods

The assessment  aims to evaluate the achievement of the following learning objectives:

-   knowledge of the multivariate analysis methods explained in the lectures

-  proper use of the explained multivariate methods to the analysis of data matrix

The exam is written and oral and the evaluation is expressed as a grade out of 30.

The evaluation of the course "Survey Sampling  and Data Analysis" is the average of the evaluations of the two units.

Teaching tools

Office hours

See the website of Marilena Pillati