INTRODUCTION TO ECONOMETRICS
Syllabus
EN
IT
Learning Objectives
LEARNING OUTCOMES:
The course provides an introduction to the tools used in Applied Microeconometrics to study causal inference. It has a practical flavor, emphasis is not on proofs but on intuitions and on applications. The course covers linear regression models, identification based on observables, randomized control trials, difference-in-differences, instrumental variables and (time permitting) regression discontinuity design. We will cover the conceptual basis of the methods in an intuitive way, and you will learn how to apply and code such methods using the software Stata. Coding in Stata will be an important component of the module. The aim is to provide students with the skills to perform data preparation and econometric analyses.
KNOWLEDGE AND UNDERSTANDING:
Knowledge of data types and fundamentals of coding on Stata, linear regression models, causal inference techniques.
APPLYING KNOWLEDGE AND UNDERSTANDING:
Ability in selecting appropriate data analysis methods, and in analysing causal relationships among variables in economics.
MAKING JUDGMENTS:
This course empowers students with the analytical skills to rigorously analyse and interpret data, enabling them to discern between correlation and causation. By applying these skills to real-world scenarios, students are equipped to critically assess causal claims in diverse contexts, enhancing their ability to make informed, independent judgments.
COMMUNICATION SKILLS:
Ability to spot and present the most suitable empirical framework for the analysis based on the nature of the data at hand and effective communication of data analysis results, also by means of graphs and tables.
LEARNING SKILLS:
Ability to learn autonomously further data analysis techniques, in professional activities or subsequent studies, achieved through the analysis of econometric methods applied in economics, finance and management.
The course provides an introduction to the tools used in Applied Microeconometrics to study causal inference. It has a practical flavor, emphasis is not on proofs but on intuitions and on applications. The course covers linear regression models, identification based on observables, randomized control trials, difference-in-differences, instrumental variables and (time permitting) regression discontinuity design. We will cover the conceptual basis of the methods in an intuitive way, and you will learn how to apply and code such methods using the software Stata. Coding in Stata will be an important component of the module. The aim is to provide students with the skills to perform data preparation and econometric analyses.
KNOWLEDGE AND UNDERSTANDING:
Knowledge of data types and fundamentals of coding on Stata, linear regression models, causal inference techniques.
APPLYING KNOWLEDGE AND UNDERSTANDING:
Ability in selecting appropriate data analysis methods, and in analysing causal relationships among variables in economics.
MAKING JUDGMENTS:
This course empowers students with the analytical skills to rigorously analyse and interpret data, enabling them to discern between correlation and causation. By applying these skills to real-world scenarios, students are equipped to critically assess causal claims in diverse contexts, enhancing their ability to make informed, independent judgments.
COMMUNICATION SKILLS:
Ability to spot and present the most suitable empirical framework for the analysis based on the nature of the data at hand and effective communication of data analysis results, also by means of graphs and tables.
LEARNING SKILLS:
Ability to learn autonomously further data analysis techniques, in professional activities or subsequent studies, achieved through the analysis of econometric methods applied in economics, finance and management.
Prerequisites
Attending students must have passed Quantitative Methods I and Quantitative Methods II from the B.D. in Business Administration and Economics, or similar courses.
The econometric methods covered in the course rely on a good mandatory knowledge of basic statistical concepts, including the following: random variable, distribution of a random variable, expectation and variance of a random variable, basic properties of probabilities and expectations (e.g., law of total probabilities, law of iterated expectations), statistical inference and linear regression models.
The econometric methods covered in the course rely on a good mandatory knowledge of basic statistical concepts, including the following: random variable, distribution of a random variable, expectation and variance of a random variable, basic properties of probabilities and expectations (e.g., law of total probabilities, law of iterated expectations), statistical inference and linear regression models.
Program
- Linear regression model: bivariate and multivariate regressions
- Omitted variable bias, partial-out interpretation of the coefficients
- Heteroskedasticity
- Hypothesis testing
- Fixed effects model
- Causal inference and potential outcome framework
- Randomized Control Trials (RCT)
- Difference-in-differences (DiD)
- Instrumental variable (IV)
- Regression Discontinuity Design (RDD)
For the first 5 weeks, 2 hours per week will be dedicated to practical sessions on Stata, during which theoretical concepts will be applied to real-life data.
- Omitted variable bias, partial-out interpretation of the coefficients
- Heteroskedasticity
- Hypothesis testing
- Fixed effects model
- Causal inference and potential outcome framework
- Randomized Control Trials (RCT)
- Difference-in-differences (DiD)
- Instrumental variable (IV)
- Regression Discontinuity Design (RDD)
For the first 5 weeks, 2 hours per week will be dedicated to practical sessions on Stata, during which theoretical concepts will be applied to real-life data.
Books
The module material (slides, datasets, Stata exercises) will be uploaded on the course webpage.
We will not follow closely any particular textbook, but the following books are highly recommended since they provide an introductory exposition of the topics we will cover:
- Angrist, J. D., & Pischke, J. S. (2009). Mostly harmless econometrics: An empiricist's companion. Princeton University Press.
- Cunningham, S. (2021) Causal Inference: The Mixtape, Yale University Press. The entire book is available online at https://mixtape.scunning.com/index.html.
- Wooldridge, J. (2019) Introductory Econometrics A Modern Approach, 7th ed. South-Western College Publishing
We will not follow closely any particular textbook, but the following books are highly recommended since they provide an introductory exposition of the topics we will cover:
- Angrist, J. D., & Pischke, J. S. (2009). Mostly harmless econometrics: An empiricist's companion. Princeton University Press.
- Cunningham, S. (2021) Causal Inference: The Mixtape, Yale University Press. The entire book is available online at https://mixtape.scunning.com/index.html.
- Wooldridge, J. (2019) Introductory Econometrics A Modern Approach, 7th ed. South-Western College Publishing
Teaching methods
During the whole duration of the course (6 weeks), there will be 3 weekly classes of 2 hours each. In all appointments, an active participation to the class will be strongly encouraged.
Exam Rules
The assessment for this course includes a final written exam along with a problem set on Stata to be completed in groups of 2 to 3 students, which constitutes 25% of the overall grade if successfully completed.
Only submissions that meet the pass criteria will count towards the grade, ensuring that students actively participate and engage with the material. Failure to pass this problem set results in the final exam counting for 100% of the entire grade. The grade of the problem set will be considered for the final mark only in the Winter sessions (October, January, February).
The final exam, conducted without access to course materials, assesses both theoretical knowledge and empirical skills through various types of questions, including true-false statements and open-ended questions that require the application to real-world examples of the econometric models studied in class.
The final evaluation is expressed out of thirty (minimum passing grade 18/30, maximum grade 30/30. Honors can be awarded to those who achieve 30/30). Students can refuse the grade (by writing it on Delphi) only during the winter sessions (October, January, February). After that, any other written evaluation will be recorded.
To pass the exam with the minimum grade of 18, the student must achieve correct numerical results, demonstrate knowledge of the essential aspects of the topics, and place them in the correct methodological context. To achieve an average grade (23-26), the student must demonstrate, in addition to a good understanding of the topics, a good analytical ability, the skill to draw correct conclusions, and proficiency in mathematical notation. A high grade (27-28) will be awarded to students who also demonstrate good judgment, can argue statements and choices, present the topics clearly and logically, use appropriate terminology, and show an understanding of mathematical proofs. Grades from 29 to 30 will be awarded to students who, in addition to meeting the previous conditions, show comprehensive presentation, precision in notation, and correct language usage. Honors are reserved for students who have achieved all objectives excellently and present concepts clearly and precisely.
Only submissions that meet the pass criteria will count towards the grade, ensuring that students actively participate and engage with the material. Failure to pass this problem set results in the final exam counting for 100% of the entire grade. The grade of the problem set will be considered for the final mark only in the Winter sessions (October, January, February).
The final exam, conducted without access to course materials, assesses both theoretical knowledge and empirical skills through various types of questions, including true-false statements and open-ended questions that require the application to real-world examples of the econometric models studied in class.
The final evaluation is expressed out of thirty (minimum passing grade 18/30, maximum grade 30/30. Honors can be awarded to those who achieve 30/30). Students can refuse the grade (by writing it on Delphi) only during the winter sessions (October, January, February). After that, any other written evaluation will be recorded.
To pass the exam with the minimum grade of 18, the student must achieve correct numerical results, demonstrate knowledge of the essential aspects of the topics, and place them in the correct methodological context. To achieve an average grade (23-26), the student must demonstrate, in addition to a good understanding of the topics, a good analytical ability, the skill to draw correct conclusions, and proficiency in mathematical notation. A high grade (27-28) will be awarded to students who also demonstrate good judgment, can argue statements and choices, present the topics clearly and logically, use appropriate terminology, and show an understanding of mathematical proofs. Grades from 29 to 30 will be awarded to students who, in addition to meeting the previous conditions, show comprehensive presentation, precision in notation, and correct language usage. Honors are reserved for students who have achieved all objectives excellently and present concepts clearly and precisely.
Attendance Rules
optional