Skip to content

Statistics and Econometrics 2 (ECO-CO-STATS2)

ECO-CO-STATS2


Department ECO
Course category ECO Compulsory courses
Course type Course
Academic year 2025-2026
Term BLOCK 2
Credits 1 (EUI Economics Department)
Professors
Contact Aleksic, Ognjen
Sessions
Syllabus Link
Enrolment info Contact ognjen.aleksic@eui.eu for enrolment details.

Description

This course introduces students to standard methods specifically designed for the analysis of microeconomic data. The first part of the course covers techniques for limited dependent variables, censoring, truncation, selection, and duration data, along with applying ML and Bayesian estimation. The potential outcomes framework for causal inference is also introduced. Additionally, the course addresses sampling and randomization designs, methods for inference, and approaches to handling missing data.
The second part of the course focuses on panel data methods, including linear and binary response models. The method of moments is reviewed, and the generalized method of moments estimation is introduced.

Learning outcomes     
By the end of the course, students will be able to:
•    Identify appropriate econometric methods to address research questions using microeconomic data.
•    Design and evaluate empirical strategies for causal inference, using tools such as the potential outcomes framework, randomized experiments, and instrumental variables.
•    Implement Bayesian estimation methods and interpret results from MCMC algorithms such as the Gibbs sampler.
•    Apply econometric models for discrete outcomes.
•    Understand and estimate models for panel data, including fixed effects, random effects, and dynamic models.
•    Conduct causal inference using methods such as difference-in-differences, event studies, and regression discontinuity designs.
•    Apply resampling techniques such as bootstrap methods for robust inference in applied research settings.
•    Understand and implement the method of moments and generalized method of moments (GMM) estimators.
•    Interpret and critically assess empirical research in microeconometrics using the tools covered in the course.
•    Translate theoretical understanding of econometric techniques into practical data analysis using statistical software.

Assessment    
•    Final Exam (70%): Open-book and open-notes exam
•    Problem Sets (30%): 4 problem sets distributed throughout the course. The problem sets can be submitted in groups (of no more than 3 students in each group). 

Module structure

WEEK 1
Potential Outcome Framework, Assignment-Based Modes of Inference
Topics: 
•    Introduction to Causal Inference
•    The Potential Outcome Framework: assumptions, finite-sample and super-popuilation causal estimands
•    Assignment mechanisms: probabilistic, unconfoundedness, ignorability
•    Inference in Randomized Experiments: Fisher’s randomization inference, Neyman’s repeated sampling approach

WEEK 2
Bayesian Inference with Application to RCTs with Noncompliance; Models for Discrete Data
Topics: 
•    Bayesian inference
•    Noncompliance in Randomized Experiments : Intention-to-Treat Approach
•    Instrumental Variables
•    MCMC algorithms: the Gibbs Sampler
•    Linear Probability Model
•    Logit and Probit
•    Maximum Likelihood
•    Marginal Effects, Standard Errors and Delta Method
•    Multinomial Logit

WEEK 3
Models for Transition Data; Estimation with Panel Data
Topics: 
•    Duration Models
•    Introduction to Panel Data
•    Fixed Effects, First Differences and Random Effects Estimators
•    TWFE Model
•    Measurement Error

WEEK 4
Difference-in-Differences; Inference with Panel Data; Dynamic models
Topics: 
•    Difference-in-differences
•    Event study design
•    Bootstrap methods – paired, residual and wild bootstrap
•    Nonlinear FE Models: Conditional Logit

WEEK 5
Generalized Method of Moments; Regression Discontinuity Design
Topics: 
•    Method of moments 
•    OLS with Clustering
•    Generalized Method of Moments
•    Dynamic Panel Models: Arellano-Bond Estimator
•    Classical Minimum Distance
•    Regression Discontinuity Design (RDD): sharp and fuzzy RDD 

Bibliography and further readings

Main References:
•    Cameron and Trivedi, Microeconometrics: Methods and Applications, Cambridge University Press, 2005
•    Joshua Angrist and Jorn-Steffen Pischke. Mostly Harmless Econometrics. An Empiricist’s Companion. Princeton University Press, 2013.
•    Jeffrey Wooldridge, Introductory Econometrics. A Modern Approach. South Western Cengage Learning, 2009
•    Deaton, Angus (1997) The Analysis of Household Surveys, free access here.
•    Arkhangelsky and Imbens (2024). Causal Models for Longitudinal and Panel Data: A Survey

 

Register for this course

Page last updated on 05 September 2023

Go back to top of the page