BARBIERI MARIA MADDALENA
Mutuazione: 21210418 Advanced topics in Statistical learning in Economia dell'ambiente, lavoro e sviluppo sostenibile LM-56 R BARBIERI MARIA MADDALENA
Objectives
The aim of the course is to provide students with a coverage of a set of methods used in the analysis of economic data to answer a variety of specific, quantitative questions and with the computational tools to be used in the empirical applications. The program includes further topics on the classical regression model, time series analysis and some recent proposal to deal with applications having many observations and/or many predictors relative to the number of observations.The course applies the widely used freeware programming environment for statistical analysis, known as R (through the RStudio interface).
Risultati Apprendimento Attesi
By the end of the course, students will be able to:Knowledge and understanding: demonstrate knowledge and understanding of the main econometric concepts and methods used to analyse time-series and panel data, as well as the foundations of econometric forecasting.
Applying knowledge and understanding: specify, estimate, and validate the econometric models introduced during the course; use R for data management and analysis, graphical presentation of results, and forecasting.
Making judgements: select the most appropriate econometric model according to the characteristics of the data and the research question; critically assess the assumptions, adequacy, and limitations of the estimated models; correctly interpret empirical results and draw conclusions consistent with the available evidence.
Communication skills: present the methods, results, and implications of an econometric analysis; use technical terminology appropriately; document and illustrate empirical analyses conducted using R, including through tables and graphical representations.
Learning skills: independently explore econometric methods for the analysis of time-series and panel data in greater depth; consult the scientific literature and the technical documentation for R packages; apply the acquired skills to new economic problems and different datasets.
Programme
A review of the multiple linear regression model.Introduction to time series analysis and forecasting. Stationarity and unit roots.
Models for univariate time series: ARMA, ARIMA, ARCH, and GARCH.
Regression models for time-series data.
Multivariate time series: cointegration and error correction models; VAR models.
Panel data: fixed-effects and random-effects models; dynamic panel data models.
Use of R and the RStudio environment to estimate and apply the models to real-world data.
The detailed syllabus and additional teaching materials will be made available on the course Moodle page.
Prerequisiti
The course requires knowledge of the main tools of descriptive and inferential statistics, as well as the fundamentals of simple and multiple linear regression models.Core Documentation
Verbeek M., A guide to modern econometrics, 2004, Wiley.Lecture notes prepared by the instructor will be made available on the course Moodle page.
Reference Bibliography
Hanck C, Arnold M., Gerber A., and Schmelzer M.. Introduction to Econometrics with R., 2024, University of Duisburg-Essen. Stock J.H. and Watson M.W., Introduction to Econometrics, Global edition, 4th Edition, 2020, Pearson. Wooldridge, J.M., Introductory econometrics: A modern approach, 2025, Cengage Hansen, B.. Econometrics. 2022, Princeton University Press. Tsay, R.S., An introduction to analysis of financial data with R, 2014, Wiley.Type of delivery of the course
Whole class teaching.Attendance
Attendance is recommended but not compulsory.Type of evaluation
The final grade is determined on the basis of the following assessment components: • assignments submitted via Moodle during the teaching period: 20% of the final grade; • written examination: 80% of the final grade. The final grade is expressed on a 30-point scale. A grade of at least 18/30 is required to pass the examination. Students who do not submit the assignments during the teaching period may replace this assessment component with a project involving the analysis of a dataset of their own choice and an oral examination. The project and the oral examination assess the same knowledge and skills as the assignments and jointly account for 20% of the final grade. The project will be discussed and assessed during the oral examination. The assignments may include multiple-choice questions, open-ended questions, and data-analysis exercises to be completed using R. The written examination lasts no more than two hours. Students are not permitted to consult books or notes during the examination. It consists of open-ended questions covering the entire course syllabus and may also require students to interpret and discuss output produced using R. Two midterm examinations, each covering a different part of the syllabus, will be held during the teaching period. Taking both midterm examinations replaces the written examination. The grade for this assessment component is calculated by assigning a weight of 30% to the first midterm examination and 70% to the second. Students who do not take both midterm examinations must sit the written examination covering the entire course syllabus. The assessment procedures, deadlines, and grading criteria will be explained at the beginning of the semester and published in a dedicated document available among the course materials on Moodle.Esempi Domande
Some examples of questions from previous years’ examinations are available on the course Moodle page.