Advanced Econometric Methods for Complex Data:
Panels, Networks and Structural VARs
Bertinoro, 19–25 July 2026
Lecturers
- Koen Jochmans, University of Toulouse
- Christiane Baumeister, University of Notre Dame, NBER, CEPR
The maximum number of allowed participants in presence is 30.
Requirements
Module 1: Knowledge of standard econometric methods (panel data, fixed-effects, basic inference).
Module 2: Basic knowledge of Bayesian analysis and SVAR models
Reading list
The reading list reflects the material that will be taught. Further material will be provided before the beginning of the course and during the lectures.
The Reading list for Module 1 and Module 2 can be downloaded from the " Pubblic attachments" section on left side column of this web page.
Course description
SIdE Summer Schools are open to scholars and practitioners of all levels and are particularly aimed at PhD students and junior researchers. They provide advanced training in modern econometric methods, combining rigorous theoretical foundations with applied perspectives and hands-on sessions.
The 2026 Summer School offers an integrated one-week program focusing on econometric modeling and inference in environments characterized by dependence, high dimensionality, and structural complexity. The School is organized in two complementary modules, taught by leading international scholars.
- Days 1–3 are devoted to panel, network, and high-dimensional econometrics, with a focus on identification, estimation, and inference in complex data structures.
- Days 4–6 focus on Bayesian identification and inference in structural VAR models, with applications to macroeconomics and policy analysis.
The program includes a Special Research Workshop with keynote lectures by both lecturers, as well as presentations by senior researchers and participants.
Module 1 (Days 1–3)
Networks, Panels & High-Dimensional Inference
Lecturer: Koen Jochmans (University of Toulouse)
Module description
This module offers a rigorous yet accessible bridge between foundational econometric techniques and cutting-edge methods for dealing with modern complex data structures: panels with large cross‐sections, network/dyadic data, latent-structure models, fixed‐effects with many covariates, non-parametric identification in network and dyadic contexts. Under the guidance of Koen Jochmans, participants will gain theoretical insights with a view to apply these methods in empirical research.
The lectures combine methodological foundations with empirical motivation and include workshops and discussion sessions aimed at fostering research design and interaction among participants.
Format: Lectures + empirical workshops + project design sessions.
Syllabus
Day 1 – Network Models and Latent Structures
- Morning: Introduction to network and dyadic data: what makes inference challenging? (incidental‐parameter problems, two‐way fixed-effects, biased estimators). Bias correction and profile-score adjustments in panel model;
- Afternoon: Semiparametric analysis of network formation, latent‐structure models.
Day 2 – Nonparametric Identification and Bootstrap Inference
- Morning: Non-parametric methods: identification in mixtures, dynamic discrete choice, latent variables.
- Afternoon: Bootstrap and robust inference in high‐dimensional contexts (many covariates, large T, large N)
Day 3 – Special Research Workshop and Keynote Lectures
The third day of the Summer School is organized as a Special Research Workshop, bringing together participants and faculty in a research-oriented setting.
The day features:
- a main keynote lecture (90 minutes) by Prof. Koen Jochmans, providing an in-depth overview of recent advances and open research frontiers in panel, network, and high-dimensional econometrics;
- presentations by senior researchers, focusing on current methodological developments and applications;
- a keynote lecture by Prof. Christiane Baumeister, offering a complementary perspective bridging econometric methodology and applied macroeconomic research;
- voluntary student presentations and discussion of ongoing research projects.
The workshop is designed to foster interaction, feedback, and research exchange among participants and lecturers.
Module 2 (Days 4–6)
A Bayesian Approach to Identification of Structural VAR Models
Lecturer: Christiane Baumeister (University of Notre Dame, NBER, CEPR)
Module description
This module focuses on Bayesian estimation and inference in structural vector autoregressive (SVAR) models, which are central tools in empirical macroeconomics. The course revisits the identification problem in SVARs and introduces a general Bayesian framework that encompasses traditional identification schemes while allowing for imperfect and incomplete identifying information.
Participants will learn how to incorporate prior information on structural parameters and shock responses and how to conduct inference in set-identified SVAR models, with applications to monetary policy, labor markets, and oil price dynamics. Lectures are complemented by hands-on Matlab sessions.
Syllabus
Day 4 – Identification of Structural VAR Models and Bayesian Analysis
- SVARs: the identification problem revisited
- identification using inequality onstraints
- A fully bayesian algorithm for SVAR estimation
- Matlab application: labor market dynamics
Day 5 – The Role of Prior Information
- Bayesian interpretation of traditional identifying assumptions
- Matlab application: oil supply and demand shocks
- Estimation of behavioral elasticities
- Prior information on structural coefficients, impacts of shocks, long-run effects and external instruments
Day 6 – Inference in Set-Identified SVAR Models
- Inference in set-identified SVAR models
- Matlab application: the effects of monetary policy
- Credibility sets for impulse response functions, variance and historical decompositions
Venue and timetables
The Module will last one week and will be held in the University Residential Centre, Via Frangipane 6, 47032 Bertinoro (FC). Participants will be hosted in the Centre guest quarters (in case of reduced availability of rooms in the Centre, they will be accommodated in local hotels).
Lectures and tutorials will be in English, with the following schedule:
- Monday to Friday: lectures 9:00-13:00, 15:00-17:00
- Saturday: lectures 9:00-13:00.
Contacts
- For more information: Roberta Partisani phone: +39 0543446554 ; e-mail: info@side-iea.it
- For administrative issues : Fabrizio Zanotti (admin@side-iea.it), phone:0543446561;
- For travel and accommodation: Roberta Partisani (rpartisani@ceub.it), phone: +39 0543446554
