88263 - STATISTICAL ANALYSIS AND MODELLING

Learning outcomes

At the end of the course, the student learn major statistical methods to deal with ecological, economical and social data, both using univariate and multivariate approaches. The student will have the capacity to deal with the practical applications of several statisical methods to real world case and data.

Course contents

Learning outcomes

At the end of the course, the student will have a good knowledge of basic and advanced multivariate statistical techniques useful to conduct statistical analysis on real dataset. The course blends theory and practice for a better understanding of the subject.

Univariate Statistics:

Descriptive statistics and introduction to statistical distributions

Location measures : mean, median, mode

Graphical representation: frequency distribution, bar graphs, histograms

Measures of scatter: range, inter-quartile range, variance

Bivariate Statistics:

Two-way tables: joint, marginal and conditional distributions

Association: independence, chi-square test

Concordance: covariance, correlation

Multivariate Statistics:

Data matrix

Mean vector

Covariance matrix

Distance Matrix

A brief introduction to the following multivariate statistical techniques: Principal Components, Cluster Analysis.

Regression:

Simple Linear Regressione

Multivariate Linear Regression

Concentration Matrix

Partial Correlation

Distributions:

Normal Distribution

Sample Mean

Statistical Hypotheses

ANOVA

Readings/Bibliography

Izenman, A. J. (2008). Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning, Springer.

Thomas H. Wonnacott, Ronald J. Wonnacott , Introductory Statistics, 5th Edition, Wiley.

Slides of the course.

Teaching methods

Frontal Lectures

Assessment methods

Written exam with TRUE/FALSE questions and exercises. (If the exam will be in presence).

 Oral exam (If it , due to COVID, will be online)

Teaching tools

Slides

Office hours

See the website of Cinzia Franceschini