The course aims to present the main approaches to the use of statistical learning and data science in the risk management context. During the course, statistical models and techniques for measuring uncertainty and risks will be introduced through empirical applications implemented in the R software.
At the end of the course the students will be able to analyze real risk datasets, choosing the relevant statistical techniques, comparing different models and correctly interpreting the obtained results.
Course Prerequisites
Descriptive statistics and basic concepts of statistical inference. Basic computer programming skills are useful, even if not formally required.
Teaching Methods
- Presentation of the analyzed data science methodologies, with a focus on the application aspects; - In-class applications and exercises with the software
Assessment Methods
Preparation and discussion of a real dataset analysis.
Texts
Slides and codes made available by the teacher. For the theoretical part, the students can refer to basic statistics texts such as (by way of example only) "An Introduction to Medical Statistics" by Martin Bland (Oxford University Press, 2015).
Contents
- Review of main concepts of probability thory and random variables; - Odds ratios and their use in risk assessment; Contingency tables analysis and Chi- Square test; - Application and validation of logistic regression models; - Survival models for the analysis of time to event data; - Cluster analysis; - Network analysis
