Bocconi 40271: Econometrics 2

Econometrics 2

Ph.D. in Economics (Bocconi University, Winter 2026)

Course Description

My course offers a modern introduction to research designs and empirical strategies in applied microeconomics, with applications across public policy, development economics, labor economics, education, marketing, and corporate finance. The focus is on causal reasoning and design-driven identification in the social sciences, providing practical insights and techniques for real-world research applications. While the course encompasses theoretical and formal econometric reasoning, its primary emphasis is on design-oriented identification from non-experimental (observational) data. I prioritize intuition over extensive formal derivations of probability theory and statistical foundations. The exploration of identification strategies builds from the prerequisites needed to replicate the conditions of an ideal experiment, which is the conceptual foundation for addressing any causal query. I examine a range of methods for assessing causal questions effectively, including the distinction between design-based and sampling-based uncertainty. Lectures are structured as self-contained modules, each dedicated to a specific identification strategy. Topics covered include regression and matching methods, instrumental variables and natural experiments, difference-in-differences designs, synthetic control methods, and regression discontinuity designs. Suggestions and guidance for implementation of these empirical strategies in applications will be discussed in my lectures and in TA sessions led by Martin Fankhauser.

Requirements

Before the semester starts. Students are expected to have strong foundations in Ph.D.-level algebra and calculus, along with a solid working knowledge of statistics and probability. You should acquire proficiency in graduate-level mathematical tools, fundamentals of probability theory, mathematical statistics, and matrix algebra before the start of classes.

After the semester starts. I strongly encourage you to engage with course materials and lecture slides before each class. Struggling with the material beforehand significantly enhances conceptual understanding and learning outcomes. You are also encouraged to develop familiarity with statistical software throughout the course, though the lectures themselves do not focus on building coding skills.

Course Readings

Lecture slides and reading materials will be made available below in advance of each class. The course integrates traditional approaches to microeconometrics with modern tools used across contemporary empirical literatures. For this reason, it is impossible to identify one textbook. Lecture time constraints will likely prevent coverage of all slide material. Topics not addressed in lectures or TA sessions can serve as a foundation for understanding additional concepts and techniques that may be useful for your own research or other courses. While lecture slides are self-contained and sufficient for understanding the core concepts, I strongly encourage you to engage with additional readings suggested below and during lectures. Consulting these supplementary materials will deepen your understanding and strengthen your future command of the methodologies covered in the course.

Exam and Problem Sets

Your final grade will be calculated as a weighted average of two components: a final exam during exam week (70% of the grade) and three problem sets (30% of the grade).

The final exam may include analytical questions or questions based on statistical software output, designed to test your ability to understand and interpret empirical results. There is no fixed exam format: I design all my exams based on the flow of discussions in class and the aspects of the course that prove most engaging. All topics covered during TA sessions are an integral part of the course and should be considered possible topics for problem sets and the final exam. Specific instructions for preparing for the exam and completing problem sets will be provided during the semester.

Detailed solutions to all problem sets will be posted shortly after each submission deadline. I strongly encourage you to study these solutions carefully, as they often provide broader conceptual insights beyond the mechanical steps required to arrive at an answer. These solutions my combine material presented in class with ideas and concepts from the suggested readings assigned throughout the course. Occasionally, I may also suggest additional readings. My solutions serve three main purposes.

Self-Assessment. They help you evaluate how well you have internalized the topics discussed in lectures and assess your readiness for the final exam. Understanding the literature. They offer insight into how contemporary research approaches causal inference across various contexts in the social sciences. Food for thought. They are designed to stimulate ideas for potential dissertation chapters, regardless of your current research interests. I strongly encourage you to think outside the box and draw on concepts from multiple subfields.

Grading

Exams are graded by assessing each question individually rather than evaluating each exam holistically. To ensure transparency, a detailed checklist outlined in the solution guide is used for grading. You can use this guide to self-assess your exam performance by comparing your answers with the checklist. The grading process involves two readings of responses for each question. In the first reading, all responses are reviewed to assess overall quality and identify common issues. This step helps determine whether difficulties stem from question phrasing or gaps in lecture clarity. In the second reading, each answer is graded using the checklist. I begin with what I identified as the strongest response during the first review and proceed systematically through all exams. This method ensures consistent differentiation of response quality across the class. After grading, each student's exam is reviewed once more to assess overall understanding and command of the subject matter for each question. Finally, letter grades are assigned based on percentage scores.

A+, A, A- denote excellent mastery of the subject and outstanding scholarship.
B+, B, B- denote good mastery of the subject and good scholarship.
C+, C, C- denote acceptable mastery of the subject.
D+, D, D- denote borderline understanding of the subject and does not represent satisfactory progress.
F denotes failure to understand the subject and unsatisfactory performance.

Lectures

LECTURE 1 (JANUARY 27, 2026). ECONOMIC REASONING, STATISTICAL LEARNING AND MICROECONOMETRICS

The Identification Zoo (Structural, Reduced Form, and Causal Parameters)
Thought Experiments vs Real (Natural) Experiments
Internal Validity, External Validity, and Statistical Validity
Potential Outcomes
Causal Estimands and Policy Relevant Probability
Potential Outcomes and Selection

Lecture slides (last revised on January 5, 2026).

Most of the terminology and concepts discussed in this part can be found in the following references:

Angrist, Joshua D., and Jorn-Steffen Pischke (2009). Mostly Harmless Econometrics. An Empiricist’s Companion, Princeton University Press. [Chapters 1 and 2]
Hernán, Miguel A., and Robins, James M. (2020). Causal Inference: What If, Boca Raton: Chapman & Hall/CRC. [Chapters 1, 6, 7 and 8]
Imbens, Guido W., and Donald B. Rubin (2015). Causal Inference for Statistics, Social, and Biomedical Sciences, Cambridge University Press. [Chapters 1, 2 and 3]
Morgan, Stephen L., and Christopher Winship (2015). Counterfactuals and Causal Inference, Cambridge University Press. [Chapter 1]
Pearl, Judea, Madelyn Glymour, and Nicholas P. Jewell (2016). Causal Inference in Statistics: A Primer, Wiley. [Chapter 1]
Rosembaum, Paul R. (2017). Observation and Experiment: an Introduction to Causal Inference, Harvard University Press. [Chapters 1 and 2]

Econometrics 2​Ph.D. in Economics (Bocconi University, Winter 2026)​

Econometrics 2

Ph.D. in Economics (Bocconi University, Winter 2026)