APPLIED STATISTICAL MODELLING | Università degli studi di Bergamo - Didattica e Rubrica

APPLIED STATISTICAL MODELLING

Attività formativa monodisciplinare
Codice dell'attività formativa: 
149016-ENG

Scheda dell'insegnamento

Per studenti immatricolati al 1° anno a.a.: 
2022/2023
Insegnamento (nome in italiano): 
APPLIED STATISTICAL MODELLING
Insegnamento (nome in inglese): 
APPLIED STATISTICAL MODELLING
Tipo di attività formativa: 
Attività formativa Caratterizzante
Tipo di insegnamento: 
Obbligatoria
Settore disciplinare: 
STATISTICA (SECS-S/01)
Anno di corso: 
1
Anno accademico di offerta: 
2022/2023
Crediti: 
9
Responsabile della didattica: 

Altre informazioni sull'insegnamento

Modalità di erogazione: 
Didattica Convenzionale
Lingua: 
Inglese
Ciclo: 
Primo Semestre
Obbligo di frequenza: 
No
Ore di attività frontale: 
72
Ore di studio individuale: 
153
Ambito: 
Statistico-matematico
Prerequisites

Good knowledge of the fundamentals of Statistics (i.e. descriptive statistics, probability, inferential statistics, simple linear regression model).

Educational goals

This course aim at offering an extensive view of the linear regression model.
As first generalization, the class of generalized linear models will be introduced. Moreover, the issues arising when a large number of covariates is available will be tackled via the penalized approach (LASSO and RIDGE regression).
In the second part of the course a gentle introduction to the Bayesian approach to statistics will be discussed in order to easily introduce multilevel and hierarchical models.
At the end of the course the student will gain the ability to:
a) choose, apply and test appropriate regression model for the analysis of different types data;
b) use the free open-source statistical software R (http://www.r-project.org) for the statistical analysis; as well as of the software Jags (https://mcmc-jags.sourceforge.io/)
c) interpret the results in a decision making perspective.

Course content

• Multiple regression
• Penalized regression (Lasso and Ridge regression)
• Generalized Linear models
• (Gentle) Introduction to Bayesian statistics and MCMC algorithms
• Bayesian multilevel models (advanced)
• Software: R, Jags for Bayesian analysis

Teaching methods

The course consists in class lectures and R/Jags lab sessions. The lectures & labs calendar will be published at the beginning of the course on the Moodle e-learning platform. Labs will take place within the hours scheduled for the course (2 hours per week, approximately).

Assessment and Evaluation

The exam consists in:
- a test including open-ended and T/F questions (concerning theoretical topics or short applications of the studied methods);
- exercises to be solved with the use of the R/Jags software (in order to evaluate the ability of the student in analysing different kind of data and in the interpretation of statistical outputs).
The two parts of the exam (theoretical and practical) are each worth 50% of the total score, approximately. A positive evaluation of the theoretical part is required in order to pass the exam.

Further information

- Attending class lectures and R labs is strongly recommended.
- If the course will be delivered online (totally or partially), changes may occur in the program and/or in the exam.
- Documentation about R software is freely available at the following link: https://www.r-project.org/other-docs.html.
- Documentation about the Jags software is freely available at the following link: https://mcmc-jags.sourceforge.io/