Tipo Insegnamento:
Obbligatoria
Durata (ore):
60
CFU:
9
SSD:
STATISTICA
Sede:
BRESCIA
Url:
Analytics e Data Science for Economics and Management/PERCORSO COMUNE Anno: 1
Anno:
2024
Course Catalogue:
Dati Generali
Periodo di attività
Primo Quadrimestre (01/10/2024 - 22/01/2025)
Syllabus
Obiettivi Formativi
The educational objectives are consistent with those characterizing the degree program in “Analytics and Data Science for Economics and Management” in which the course is inserted. The course is concerned with the development, use and discussion of the main statistical methods of models of statistical learning useful for the analysis of complex data, to develop evidence-based answers to relevant questions and then give a valid support to strategic decisions in the fields of economics, marketing, management control, business intelligence and social sciences.
Case studies and applications are proposed in socioeconomics and management fields, with the final aim of learning how to react to challenges of big data and data-driven economy. Using real cases and applications, the course aims at providing operational and practical guidance to data science, useful to those who, in various corporate functions as well as in public institutions, are involved in collecting, analyzing, processing and evaluating qualitative and quantitative information related to socioeconomic and company data.
In detail, students will gain the following skills:
1) Knowledge and understanding: by means of a gradual learning process, linking the contents of this course with the educational objectives of the cycle degree program in which the course is inserted, students will acquire the methodological and applied knowledge about the main concepts of statistical learning and will be able to apply such knowledge by means of appropriate software.
2) Applying knowledge and understanding: students will be able to implement statistical regression and classification models in order to extract proper information from data, useful to analyse real phenomena in several fields of economics and management, and to understand their most important aspects.
3) Making judgements: students who successfully complete this course will be able to select the most appropriate statistical models, apply sound statistical methods, perform the analyses using statistical software, and organize results in order to draw conclusions and decide in uncertain situations, like in specific economic and business situations.
4) Communication skills: students who successfully complete this course will be able to communicate, to experts and non-experts, data information and evaluations, also with the help of outputs from specific software and data visualization devices.
5) Learning skills: the course is aimed to provide the methodological and applied knowledge of statistical learning, necessary to address subsequent studies, in particular the advanced courses in mathematics, statistics, computer science, the quantitative aspects of economics courses, the applied projects in laboratories and internships, the empirical analyses in the final thesis.
Case studies and applications are proposed in socioeconomics and management fields, with the final aim of learning how to react to challenges of big data and data-driven economy. Using real cases and applications, the course aims at providing operational and practical guidance to data science, useful to those who, in various corporate functions as well as in public institutions, are involved in collecting, analyzing, processing and evaluating qualitative and quantitative information related to socioeconomic and company data.
In detail, students will gain the following skills:
1) Knowledge and understanding: by means of a gradual learning process, linking the contents of this course with the educational objectives of the cycle degree program in which the course is inserted, students will acquire the methodological and applied knowledge about the main concepts of statistical learning and will be able to apply such knowledge by means of appropriate software.
2) Applying knowledge and understanding: students will be able to implement statistical regression and classification models in order to extract proper information from data, useful to analyse real phenomena in several fields of economics and management, and to understand their most important aspects.
3) Making judgements: students who successfully complete this course will be able to select the most appropriate statistical models, apply sound statistical methods, perform the analyses using statistical software, and organize results in order to draw conclusions and decide in uncertain situations, like in specific economic and business situations.
4) Communication skills: students who successfully complete this course will be able to communicate, to experts and non-experts, data information and evaluations, also with the help of outputs from specific software and data visualization devices.
5) Learning skills: the course is aimed to provide the methodological and applied knowledge of statistical learning, necessary to address subsequent studies, in particular the advanced courses in mathematics, statistics, computer science, the quantitative aspects of economics courses, the applied projects in laboratories and internships, the empirical analyses in the final thesis.
Prerequisiti
Descriptive and inferential statistics, basic knowledge of R programming.
Metodi didattici
Lessons and practicals with use of computer
Verifica Apprendimento
The exam covers all the topics in the Program and consists of two parts:
(1) an online test on the Moodle e-learning platform including one open-ended and 5 closed-ended questions concerning theoretical topics and/or short applications of the studied methods; the overall grade of this test amounts to 16 maximum (6 for the open-ended question and 2 for each of the closed-ended questions);
(2) a poster exam, consisting in a 5-minute presentation of a poster showing the results of a group project of data analysis using R, followed by an individual oral exam. In detail, a group of students prepare the project, the poster and its presentation. Students are graded on the content, organization and design of the poster itself, the oral presentation of the poster and the ability to answer questions on the poster. The grading of the poster exam occurs in two parts: the group grade (max 8) and an individual grade (max 8 points); the latter is based on a brief individual oral examination administered to each student in the poster group. Although students are permitted to “tag-team” the presentation, it is recommendable that each group chooses one person to be responsible for the presentation.
Only at the teacher’s discretion, the poster exam can exceptionally be replaced by a computer-based test, carried out in the computer lab, requiring the analysis of one or more data sets using R and the interpretation of the obtained results. Students can carry out this test with the help of the course material.
Final Evaluation:
The two parts of the exam (online test and poster exam) are each worth 50% of the total score. The final grade is obtained as the sum of the two grades in the two parts. The exam is passed if the final grade is greater than or equal to 18. It will be given a final grade of 30/30 cum laude to the students who achieve a final score equal to 32.
There are no differences between attending and non-attending students.
In order to be able to sit for the exams, students must register through the Esse3 platform within the deadlines. Students who have not registered for the exam cannot take the exam.
In addition, students must communicate to the teacher (by email) at least 5 days before the exam day if they intend to do the written exam, the poster exam, or both. Those who want to do the poster exam must communicate the team composition at least 10 days before the exam day and deliver, at least 1 day before the exam day, a zip folder containing (i) data, (ii) R script, and (iii) poster file or other relevant files used for poster preparation. The email used for these communications does not replace the registration through the Esse3 platform.
The online test is aimed at verifying skill 1 (Knowledge and understanding).
The poster exam (or the computer-based test) allows to verify skills 2, 3 and 4 (Applying knowledge and understanding, Making judgements, Communication skills).
The skill concerned with autonomous study (5, Learning skills) is indirectly verified, because passing the exam is also made possible by the autonomous execution of exercises suggested by the teacher for homework.
(1) an online test on the Moodle e-learning platform including one open-ended and 5 closed-ended questions concerning theoretical topics and/or short applications of the studied methods; the overall grade of this test amounts to 16 maximum (6 for the open-ended question and 2 for each of the closed-ended questions);
(2) a poster exam, consisting in a 5-minute presentation of a poster showing the results of a group project of data analysis using R, followed by an individual oral exam. In detail, a group of students prepare the project, the poster and its presentation. Students are graded on the content, organization and design of the poster itself, the oral presentation of the poster and the ability to answer questions on the poster. The grading of the poster exam occurs in two parts: the group grade (max 8) and an individual grade (max 8 points); the latter is based on a brief individual oral examination administered to each student in the poster group. Although students are permitted to “tag-team” the presentation, it is recommendable that each group chooses one person to be responsible for the presentation.
Only at the teacher’s discretion, the poster exam can exceptionally be replaced by a computer-based test, carried out in the computer lab, requiring the analysis of one or more data sets using R and the interpretation of the obtained results. Students can carry out this test with the help of the course material.
Final Evaluation:
The two parts of the exam (online test and poster exam) are each worth 50% of the total score. The final grade is obtained as the sum of the two grades in the two parts. The exam is passed if the final grade is greater than or equal to 18. It will be given a final grade of 30/30 cum laude to the students who achieve a final score equal to 32.
There are no differences between attending and non-attending students.
In order to be able to sit for the exams, students must register through the Esse3 platform within the deadlines. Students who have not registered for the exam cannot take the exam.
In addition, students must communicate to the teacher (by email) at least 5 days before the exam day if they intend to do the written exam, the poster exam, or both. Those who want to do the poster exam must communicate the team composition at least 10 days before the exam day and deliver, at least 1 day before the exam day, a zip folder containing (i) data, (ii) R script, and (iii) poster file or other relevant files used for poster preparation. The email used for these communications does not replace the registration through the Esse3 platform.
The online test is aimed at verifying skill 1 (Knowledge and understanding).
The poster exam (or the computer-based test) allows to verify skills 2, 3 and 4 (Applying knowledge and understanding, Making judgements, Communication skills).
The skill concerned with autonomous study (5, Learning skills) is indirectly verified, because passing the exam is also made possible by the autonomous execution of exercises suggested by the teacher for homework.
Testi
Course materials and lecture slides available on the e-learning platform.
An introduction to Statistical Learning, 2nd edition, James G., Witten D., Hastie T., Tibshirani R., Springer, 2021, ISBN 9781461471370, https://hastie.su.domains/ISLR2/ISLRv2_website.pdf
An introduction to Statistical Learning, 2nd edition, James G., Witten D., Hastie T., Tibshirani R., Springer, 2021, ISBN 9781461471370, https://hastie.su.domains/ISLR2/ISLRv2_website.pdf
Contenuti
Main methods and models of statistical learning for modeling and understanding complex datasets, with a focus on supervised learning, with regression and classification methods. Contents include extensions of linear regression model, polynomial regression, logistic regression, and linear discriminant analysis; models for categorical data; resampling methods (cross-validation and bootstrap), linear model selection and regularization methods (subset selection, shrinkage methods, dimension reduction methods); nonlinear models, splines and generalized additive models. Computing is done in R, with possible integration of data analysis software that utilizes the R environment for statistical computing, through tutorial sessions and homework assignments. Case studies and applications focus on digital economy and management.
Lingua Insegnamento
English
Altre informazioni
If the computer lab cannot be used, students are required to bring their own laptops
Corsi
Corsi
Analytics e Data Science for Economics and Management
Laurea Magistrale
2 anni
No Results Found