Statistics, econometrics and applications
A.A. 2025/2026
Obiettivi formativi
The course provides students with a working knowledge of probability and statistics, skills in data handling and statistical programming, and an understanding of the models and methods of applied econometrics. It equips students with the essential tools for statistical analysis, also introducing a Bayesian perspective for inference and decision-making. Building on these foundations, the course presents the linear regression model, starting with a single regressor and extending to multiple regressors, and examines the properties of the OLS estimator. It then addresses key econometric challenges such as heteroskedasticity, autocorrelation, and endogeneity through techniques including generalized least squares and instrumental variables. The analysis is further extended to panel data and discrete choice models. Practical applications in economics are central to the course, with students consolidating their knowledge through applied problem sets carried out with statistical software.
Risultati apprendimento attesi
After completing the course, students will be able to specify linear regression models, estimate coefficients, and perform hypothesis testing; understand the properties of estimators (unbiasedness, efficiency, consistency, and asymptotic normality) in order to assess the appropriateness and limitations of different econometric approaches; identify and address key issues such as nonlinearity, heteroskedasticity, autocorrelation, and endogeneity; develop and apply Bayesian models; understand and apply econometric methods for panel data and discrete choice models; use statistical software to produce and interpret empirical results for policy and real-world economic issues; and critically evaluate econometric analyses, including policy reports and academic research. These outcomes will also enable students to engage with empirical analyses presented in other courses and provide them with quantitative tools for their final thesis.
Periodo: Secondo semestre
Modalità di valutazione: Esame
Giudizio di valutazione: voto verbalizzato in trentesimi
Corso singolo
Questo insegnamento può essere seguito come corso singolo.
Programma e organizzazione didattica
Edizione unica
Responsabile
Periodo
Secondo semestre
Programma
The course equips students with working knowledge of the tools of probability and statistics, with skills in data handling and statistical programming, and with an understanding of the models and methods of applied econometrics. To this aim, problem sets with both analytical and computer-exercise components will be a relevant part of the course.
Main topics
0. Basics refresher: probability and random variables.
1. Bayesian inference: models and computation.
2. The linear regression model with a single regressor: estimation through ordinary least squares, reading and interpreting the regression output, using the model for prediction. The linear regression model with multiple regressors.
3. Checking assumptions of the regression model: functional form, multicollinearity, heteroskedasticity, autocorrelation, non-normality.
4. Using the model to investigate causal relationships: omitted variables, endogenous regressors and the method of instrumental variables.
5. Analysis of panel data: fixed effects estimator, random effects estimator, specification tests, Hausman-Taylor estimator.
6. Models for binary dependent variables: probit and logit models.
Main topics
0. Basics refresher: probability and random variables.
1. Bayesian inference: models and computation.
2. The linear regression model with a single regressor: estimation through ordinary least squares, reading and interpreting the regression output, using the model for prediction. The linear regression model with multiple regressors.
3. Checking assumptions of the regression model: functional form, multicollinearity, heteroskedasticity, autocorrelation, non-normality.
4. Using the model to investigate causal relationships: omitted variables, endogenous regressors and the method of instrumental variables.
5. Analysis of panel data: fixed effects estimator, random effects estimator, specification tests, Hausman-Taylor estimator.
6. Models for binary dependent variables: probit and logit models.
Prerequisiti
Students are expected to be familiar with the basic concepts of matrix algebra and to have completed an introductory course in probability and statistics.
Metodi didattici
- Theoretical lectures delivered in person.
- Practical sessions using RStudio and Stata, during which students will be required to solve problem sets using their laptops.
- Practical sessions using RStudio and Stata, during which students will be required to solve problem sets using their laptops.
Materiale di riferimento
- Hill-Griffiths-Lim, Principles of Econometrics, 5th Edition, Wiley.
- Greene, Econometric Analysis, 8th Edition, Pearson.
- Stock-Watson, Introduction to Econometrics, 4th Edition, Pearson.
- Online resources on Bayesian methods (course website on Ariel).
- Greene, Econometric Analysis, 8th Edition, Pearson.
- Stock-Watson, Introduction to Econometrics, 4th Edition, Pearson.
- Online resources on Bayesian methods (course website on Ariel).
Modalità di verifica dell’apprendimento e criteri di valutazione
The exam assesses whether students have achieved the course learning objectives, such as selecting appropriate models for research questions, interpreting econometric software output, performing relevant tests, and applying statistical models to support economic decision-making.
The exam consists of three parts:
- Part 1. Statistics (mandatory): A written test with several open-ended questions. These may be theoretical and/or require interpretation of R output. Maximum points awarded: 14. Minimum score to pass: 7.
- Part 2. Econometrics (mandatory): A written test with two exercises, each including multiple open-ended questions. The exercises may be theoretical or based on applied analysis (e.g., interpretation of Stata output). Maximum points awarded: 14. Minimum score to pass: 7.
- Part 3. Project work (optional): A group project (teams of two or three students), requiring the submission of a written report on a case study. Maximum points awarded: 3.
Students must pass both Part 1 and Part 2 to complete the exam successfully. Part 3 is optional. The final grade will be a single score, calculated as the sum of the grades from the three parts. To pass Part 1 and Part 2, students must obtain at least 7 points in each of them, and the sum of the two grades should be at least 18. The final grade is measured on a 30-point scale. A total score of 31 corresponds to a grade of 30 cum laude.
The exam consists of three parts:
- Part 1. Statistics (mandatory): A written test with several open-ended questions. These may be theoretical and/or require interpretation of R output. Maximum points awarded: 14. Minimum score to pass: 7.
- Part 2. Econometrics (mandatory): A written test with two exercises, each including multiple open-ended questions. The exercises may be theoretical or based on applied analysis (e.g., interpretation of Stata output). Maximum points awarded: 14. Minimum score to pass: 7.
- Part 3. Project work (optional): A group project (teams of two or three students), requiring the submission of a written report on a case study. Maximum points awarded: 3.
Students must pass both Part 1 and Part 2 to complete the exam successfully. Part 3 is optional. The final grade will be a single score, calculated as the sum of the grades from the three parts. To pass Part 1 and Part 2, students must obtain at least 7 points in each of them, and the sum of the two grades should be at least 18. The final grade is measured on a 30-point scale. A total score of 31 corresponds to a grade of 30 cum laude.
SECS-P/05 - ECONOMETRIA - CFU: 9
Esercitazioni: 16 ore
Lezioni: 64 ore
Lezioni: 64 ore
Docente/i
Ricevimento:
Giovedì 16:30-18:00 (è necessario richiedere un appuntamento via email)
Microsoft Teams
Ricevimento:
Su appuntamento Martedì e Mercoledì (email)
via Celoria 10