ECONOMETRICS LABORATORY

The Laboratory of Econometrics is an essential complement to the theoretical Econometrics course. It offers first-year Master’s students in Economics and Finance the opportunity to apply in practice the quantitative tools acquired in class. While the theoretical course focuses on the formal construction of econometric models — based on mathematical and probabilistic foundations — the Laboratory provides the context to implement these models in the analysis of real-world economic and financial data.

Due to time constraints, the theoretical course cannot cover in depth the many operational aspects involved in empirical work. Yet practical application is crucial: even a simple linear regression can yield misleading or distorted results if applied without methodological rigour, despite appearing formally correct.

The Laboratory aims to develop students’ methodological awareness and practical skills for sound empirical analysis. Through hands-on exercises using real datasets — reflecting current macroeconomic conditions or financial market dynamics — students become familiar with data handling, model specification and estimation, and the critical interpretation of results.

These skills are of fundamental importance for the successful completion of the Master’s thesis and for future employment, where the ability to analyse data and construct quantitative models is increasingly in demand in the field of economics and finance.

Knowledge and understanding
At the end of the course, students will have acquired solid knowledge of the main procedures for empirical analysis of economic and financial data, with particular emphasis on the specification, estimation, and validation of regression models.
They will also understand the limitations of theoretical models when applied to real data, and will develop the ability to combine statistical, economic, and computational knowledge to interpret results accurately. Attention will be given to the diagnosis of common errors, the economic relevance of results, and the evaluation of data quality.

Applying knowledge and understanding
Students will be able to apply econometric tools to real-world datasets from official sources (e.g., FRED St. Louis, Eurostat, ECB, ISTAT, etc.) and independently carry out a complete empirical analysis: from data import and preparation, to model specification and critical interpretation of results.
They will learn to use econometric software and programming environments such as EViews, and will also be introduced to the use of Python and the appropriate application of AI in solving practical quantitative problems in macroeconomic and financial contexts.
They will develop applied problem-solving skills, including the ability to identify and address issues such as specification of static and dynamic models, residual analysis, model misspecification, response to exogenous shocks, and transitions between equilibrium states in economic systems.

Making judgements
Students will develop the ability to critically assess the reliability of empirical findings and to reflect on methodological choices and data limitations.
They will be able to propose modifications and improvements to existing analyses, justifying technical decisions with coherent reasoning.

Communication skills
Students will be able to effectively communicate the results of an empirical analysis through the drafting of a short technical report and an oral presentation summarizing key findings and economic implications.
They will also learn to adapt their communication style to suit different audiences (academic or professional).

Learning skills
Students will strengthen their ability to independently learn new econometric tools and methods, by consulting academic literature and technical documentation.
The Laboratory fosters an active learning approach, encouraging analytical curiosity and a mindset of continuous development — essential for working in fast-evolving professional environments.

To successfully attend the Laboratory of Econometrics, students are expected to have acquired the basic knowledge provided in the Econometrics course, which is considered a prerequisite.
The course in Econometrics (in Italian or English) may also be taken concurrently with the Laboratory, allowing students to benefit from the simultaneous integration of theoretical and practical components.

In particular, students should be familiar with:

the fundamental concepts of linear regression (classical linear model, interpretation of coefficients, OLS estimation);

the main assumptions of the linear model and the issues arising when these assumptions are violated (heteroskedasticity, autocorrelation, multicollinearity);

basic elements of inferential statistics (hypothesis testing, confidence intervals, p-values);

basic knowledge of linear algebra and probability.

Many of these concepts will be reviewed and applied concretely throughout the Laboratory.

Students are also expected to have basic operational skills in the use of digital tools, including spreadsheets and data processing software.

Introductory knowledge of EViews or of a programming language such as Python or R is useful, though not mandatory.

The Laboratory is also designed to guide students in the practical use of these software tools, particularly in the stages of model specification, estimation, and validation.

The course typically benefits from the presence of a tutor who supports students through the different stages of their learning journey, providing targeted interactions, clarifications, and practical assistance with software tools.

The Laboratory of Econometrics is designed to develop advanced practical skills in the empirical analysis of economic and financial data. The course follows a progressive structure that links theoretical foundations to real-world application, using actual datasets and specialized econometric software.

Compared to undergraduate-level courses, this Laboratory emphasizes greater methodological depth and focuses on the student’s ability to critically address complex economic problems through quantitative modeling.

The program is structured into the following key stages:

Defining the research objective and selecting the dependent variable

Choosing the sample period for model specification

Selection of explanatory variables

Time series with different frequencies

Conversion from high to low frequency

Distinction between stock and flow variables

Conversion from low to high frequency

Seasonally adjusted vs. non-adjusted series

Seasonal adjustment methods

Descriptive analysis of time series

Graphical exploration

Empirical distribution analysis and functional transformations

Correlogram analysis

Analysis of variable integration

ADF test procedure and interpretation

Testing the order of integration

Regression analysis

Estimation of the static model

Cointegration analysis

Long-run equilibrium curve

Long-run relationships: relevance and impact measures

Marginal effects, propensities, elasticities

Statistical significance, standardized coefficients, partial correlations

Estimation of the dynamic model

Initial dynamic model based on static regression variables

Regressor selection and elimination of irrelevant variables

Extended model with additional regressors

Residual analysis of the restricted dynamic model

Fitting reconstruction of the dependent variable in-sample

Evaluation of forecast performance (in-sample fit)

Forecasting

Long-run forecast curve

Goodness-of-fit tests for predicted values

Static forecast from the restricted dynamic model

Short-run static forecast of the dependent variable in levels

Dynamic forecast from the model

Implicit vs. explicit formulation of the ECM regressor

Comparison with a statistical benchmark model

Impulse Response Functions

Transitions between equilibrium states: practical examples

All topics are explored through hands-on exercises using econometric software (primarily EViews, or with an introduction to Python). The course concludes with a final project in which students apply the full analysis pipeline to an empirical problem of their choice, simulating the structure of a Master's thesis or a professional report.

The main course material is an original text made available to students on the Moodle platform. It provides a complete and guided empirical analysis of a real macroeconomic variable — for example, the Personal Consumption Expenditure (PCE) in the United States.

The text covers all operational phases of empirical work, in line with the course content, and serves as a practical reference for applying the methods discussed in class.

Additional resources — including selected readings, academic articles, and technical documentation for the software used — will also be provided via Moodle throughout the course.

The student discusses the written project he has carried out following the example commented during the course.
The positive outcome of the discussion allows the student to obtain the evaluation of the exam in thirtieths.
Alternatively, the student can ask to obtain 6 CFU as an internship, regardless of having inserted the teaching in his study plan or not.

oral

The final grade is expressed on a 30-point scale, with 18/30 as the minimum passing mark and 30/30 as the maximum. In case of outstanding performance, the grade “30 cum laude” (with honours) may be awarded.

Evaluation is based on the written project, the correctness of the empirical analysis, the student’s mastery of applied tools, and the ability to interpret the results critically.

If the student chooses to convert the activity into an internship, no numerical grade is assigned. Instead, 6 ECTS credits are granted administratively, following the instructor’s communication to the Departmental Academic Office.

The course is delivered in a laboratory-based format with a strongly interactive and practical approach. The instructor has 30 academic hours distributed over 5 weeks, during which students are guided in the study of a real economic process using multivariate regression analysis.

Teaching activities include:

applied lectures with code demonstrations and interpretation of empirical results;

individual exercises on datasets provided by the instructor;

group discussions on issues related to model specification, interpretation, and validation.

Active student participation is encouraged, especially through the discussion of alternative methodological choices.

Specialized software (EViews, Python) and technical documentation are used throughout the course and are made available on Moodle.

The tutor assists students in developing their individual project — from choosing the economic case study to guiding them through the stages of model specification, estimation, and analysis — providing practical and methodological support.

The final project is developed progressively and represents the culmination of the work done during the course, with continuous feedback from both the instructor and the tutor.

Ca’ Foscari abides by Italian Law (Law 17/1999; Law 170/2010) regarding support services and accommodation available to students with disabilities. This includes students with mobility, visual, hearing and other disabilities (Law 17/1999), and specific learning impairments (Law 170/2010). If you have a disability or impairment that requires accommodations (i.e., alternate testing, readers, note takers or interpreters) please contact the Disability and Accessibility Offices in Student Services: disabilita@unive.it.

This subject deals with topics related to the macro-area "Poverty and inequalities" and contributes to the achievement of one or more goals of U. N. Agenda for Sustainable Development