LEARNING OUTCOMES

The teaching imparts to the student the fundamentals of statistical models useful for the quantitative analysis of economic and social phenomena. The student will be able to produce statistical reports with the help of data tables, graphs and more sophisticated tools such as multiple regression, logistic regression and some modern multivariate analysis techniques. The teaching is application-oriented and several hours will be devoted to an introduction to data analysis software such as Microsoft Excel and R (R-Studio).

AIMS AND LEARNING OUTCOMES

The primary objective of the teaching is to give the student a broad overview of classical and more modern statistical methods for the analysis of economic and social phenomena. This is achieved by alternating between two teaching phases: lectures and computer-based exercises in the statistical environment R (R-Studio). 

• Knowledge and understanding Students acquire adequate knowledge of the fundamentals of inferential statistical analysis and data analysis in the R-statistical environment.
• Ability to apply knowledge and understanding Students are able to interpret the results of statistical analyses and produce their own for the understanding of economic, social and demographic phenomena.
• Autonomy of judgement Students are able to assess the quality of the analyses conducted and to make decisions based on the results of the statistical analyses conducted.
• Communication skills Students acquire the basic statistical vocabulary to communicate clearly and unambiguously with specialist and non-specialist speakers.
• Learning skills Students are able to independently study other statistical methods not presented in the course of teaching and in particular to approach econometric analysis.

Knowledge:

• fundamental elements of descriptive and inferential statistical analysis with particular regard to regression models
• analysis and programming in the statistical environment R

Skills:

• ability to independently read, interpret and produce a statistical report 
• ability to autonomously process data 

PREREQUISITES

Although there are no formal prerequisites, it is useful for students to have a basic knowledge of statistics with particular regard to descriptive analysis for quantitative variables and principles of regression analysis.

TEACHING METHODS

Lectures with computer room exercises

SYLLABUS/CONTENT

Part I - The foundations of economic and social statistical analysis

1. Fundamentals of descriptive statistics
2. Introduction to the calculus of probability
3. Statistical inference
   • Estimation, estimators and the distribution of estimators
   • Confidence intervals
   • Hypothesis testing
4. Linear regression models: descriptive and inferential analysis

Part II - Introduction to Statistical Learning

1. Introduction to statistical learning and the R-analysis environment in R-Studio
2. Multiple linear regression
3. Classification problems and logistic regression
4. The choice of linear model and regularisation 
5. Tree-based methods
6. Neural networks
7. Other unsupervised learning methods

RECOMMENDED READING/BIBLIOGRAPHY

James G., Witten D., Hastie T. and Tibshirani R. (2021). Introduction to statistical learning, Springer. Freely available online at: https://www.statlearning.com/