### Social sciences and humanities

## Subject: INTRODUCTION TO ECONOMETRICS (A.A. 2025/2026)

### degree course in ECONOMICS AND FINANCE

Course year | 3 |
---|---|

CFU | 6 |

Teaching units |
Unit Introduzione all'econometria
A11 (lesson)
- TAF: Supplementary compulsory subjects SSD: SECS-P/01 CFU: 6
Barbara PISTORESI |

Exam type | written |

Evaluation | final vote |

Teaching language | Italiano |

### Teachers

### Overview

The course introduces univariate and multivariate regression analysis and some extensions of the basic model. Particular attention is given to the students' ability to apply the concepts learned through regression analysis (in the computer lab) to be carried out on databases that cover a wide range of problems (Capital asset pricing model, term structure of interest rates, income and substituion effects in the demand functions, returns to education, gender wage gaps, the determination of real estate prices, consumption and family structure, taxation and demand for alcohol, mortality rates on roads and effectiveness of the laws on driving under the influence of alcohol, etc.). To develop the topics covered, we will use the software Gretl .

### Admission requirements

Basic knowledge of introductory statistics.

### Course contents

1.What is econometrics. the different types of economic data: cross section, longitudinal, time series. the notion of causality.

2.The simple linear regression model. Ordinary least squares. Algebric and statistical properties of estimators. Unit of measurement and functional form.

3.The multiple regression model. Omitted variable bias. Expected value and variance of estiamtors, multicollinearity, Gauss-Markov theorem.

4.Inference in the multiple regression model. t test, p-value, confidence interval, F test.

5.Model selection SER (standard error of the regression, information criteria (AIC and BIC). Examples and applications in Gretl.

6.Heteroscedasticity of the ols estimator. White test. correction of Heteroscedasticity: estimation of robust standard errors; use of logs; GLS estimator (hints).

7.Regression with dummy variables.

8.Non linear regression: non linear function of a single indipendent variable. Polinomials. Logarithms (models lin-log; log-lin, log- log).

9.Non linear regression: interactions among independent variables (dummies and continuous).

### Teaching methods

frontal lectures with both a theoretical and applied content. We will use the software Gretl for econometric analysis and also Excel for the analysis of datasets. Lectures are held both in the computer lab and in a standard classroom. Lectures, exercises, and other materials are available on Moodle.

### Assessment methods

Both attendance to lectures and a final written exal of one hour and a half on theoretical question and questions on empirical analysis to be solved using Gretl.

### Learning outcomes

Following the 5 Dublin descriptors:

1 Knowledge and ability to understand. Through lectures, tutorials, autonomous exercises and collegial discussion of the results, the student learns the basic statistical techniques to be applied to economic data.

2 Capacity to apply knowledge and understanding. Through tutorials that use the econometric software Gretl, the student is able to manage databases with which to estimate the parameters of economic models, to subject these models to test, to predict economic variables, and finally can conduct an analysis on economic policy topics.

3 Autonomy of judgement in critically evaluating the exercises and tutorials regarding points 1 and 2.

4. Communicative abilities. The classroom presentation of the results obtained with computer analysis processing helps the student to argue and discuss the choice of the statistical techniques more appropriate to the type of problem analyzed and his ability to present the results. Finally, the group discussion helps the critical evaluation of the work done.

5. Learning ability. The activities described above enable the student to acquire the basic knowledge of econometric tools for the elaboration of economic data. These skills will be useful for further studies to address more advanced econometrics courses or to develop on their own quantitative analysis that may be required in economics courses or in a dissertation.

### Readings

- C. Hill, W. E. Griffiths, G. C. Lim, Principi di econometria, Zanichelli.