EABCN Online Training School: Causal Inference with VARs

Euro Area Business Cycle Network Online Training School

Causal Inference with VARs
by Giovanni Ricco (CREST–École Polytechnique, University of Warwick & CEPR)

10-12 November 2025
Online via Zoom

Submission Deadline: 6 pm GMT (UK Time), 8 September 2025

General Description

We are pleased to announce the latest EABCN Training School; a three-day course entitled "Causal Inference with VARs" taught by Professor Giovanni Ricco (CREST–École Polytechnique, University of Warwick & CEPR).

It is primarily aimed at participants in the Euro Area Business Cycle Network, but applications will also be considered from doctoral students, post-doctoral researchers and economists working in central banks and government institutions outside of the network, as well as commercial organisations (fees are applicable for non-network non-academic organisations).

This course provides a comprehensive introduction to causal inference in Vector Autoregressions (VARs), with a focus on structural identification approaches widely used in empirical macroeconomics, and some key applications on monetary policy.

The course develops the theoretical underpinnings of VAR models, reviews leading identification techniques, and discusses recent advances in the use of statistical restrictions, and instrumental variables for structural analysis. Participants will gain a deep understanding of how to use VAR models to study the propagation of economic shocks and measure their dynamic effects, with attention to both methodological rigor and practical implementation.

Tentative course outline

DAY 1: VAR and SVAR, the challenges of identification
Lecture Session: 9:00 to 12:00 CET
Practical Session: 14:00 to 16:00 CET

The first day introduces the Slutsky-Fisher framework to motivate VARs, the basics of VARs, the Wold representation and emphasizing their role in modelling macroeconomic dynamics and forecasting. The lecture discusses the map linking reduced-form VAR and structural VARs (SVARs) in the cases of invertibility, recoverability and non-recoverability. Key concepts such impulse response functions, and forecast error variance decompositions are presented. The session concludes with an overview of the identification problem and the economic rationale for imposing restrictions.

DAY 2: Statistical identification
Lecture Session: 9:00 to 12:00 CET
Practical Session: 14:00 to 16:00 CET

The second day focuses on statistical approaches to identifying structural shocks in VAR models. It begins with classical methods, including short-run and long-run restrictions, as well as recursive identification via Cholesky decomposition. The lecture then explores more flexible approaches such as sign restrictions, identification via heteroskedasticity and max-share identification.

DAY 3: Instrumental variables and VARs
Lecture Session: 9:00 to 12:00 CET
Practical Session: 14:00 to 16:00 CET

The final day turns to identification strategies based on instrumental variables (IVs), a powerful and increasingly popular approach in the SVAR literature. The lecture introduces proxy/IV SVARs and discusses the conditions under which external instruments can be used to recover structural shocks. Special attention is given to the construction of valid instruments, including those based on high-frequency data and narrative shocks. The session covers estimation techniques and the interpretation of impulse responses obtained through IV methods, concluding with recent applications and evidence from empirical studies.

Administrative Information

We ask that you send a current version of your CV. PhD students must also specify in
which way the school will be useful for their current research (max 300 words).

The course will take place online via Zoom. More details will be circulated closer to the date to successful applicants.

Participants from non-academic institutions where the employer is not a member of the
EABCN network are charged a course fee of EUR1000.

How to apply:

Candidates who are CEPR affiliated or already have a CEPR profile should apply by submitting their CV online:

1. Log in on the CEPR hub online at https://hub.cepr.org/
2. Go to https://hub.cepr.org/event/4833
3. Click on "Step 1: Apply"
4. Complete the requested information and upload the required documentation:
   Applications without the required documents will not be considered.
   a. All applicants must submit a CV. PDF or word document is preferred but the option to provide a link to CV is available.
   b. PhD Students must include a supporting statement (max 300 words) specifying how the school will be useful for their current research.
   i. To do so click ‘Would you like to submit additional files?’.
   ii. Upload PDF or Word Document.
   iii. The Supporting Statement must be in a document separate from the CV file.
5. Click "Submit Information".

Candidates who are not CEPR affiliated or do not have a CEPR profile should apply by submitting their CV online:

1. Create an online profile at https://hub.cepr.org/user/register
2. Log in on the CEPR hub online at https://hub.cepr.org/
3. Go to https://hub.cepr.org/event/4833
4. Click on "Step 1: Apply"
5. Complete the requested information and upload the required documentation:
   Applications without the required documents will not be considered.
   a. All applicants must submit a CV. PDF or word document is preferred but the option to provide a link to CV is available.
   b. PhD Students must include a supporting statement (max 300 words) specifying how the school will be useful for their current research.
   i. To do so click ‘Would you like to submit additional files?’.
   ii. Upload PDF or Word Document.
   iii. The Supporting Statement must be in a document separate from the CV file.
6. Click "Submit Information".

If you have any difficulty in applying please contact Bao Khanh Le, Senior Events Officer for assistance.

About the Instructor:

Giovanni Ricco is a Professor of Economics at CREST–École Polytechnique and the University of Warwick, serving also as a Chercheur Associé at OFCE–Sciences Po and a Research Affiliate at CEPR. As an expert in macroeconomics and time‐series econometrics, his research focuses on fiscal and monetary policy, models under imperfect information, and structural VAR identification using external instruments. Giovanni holds a PhD in Economics from London Business School, and a PhD in Physics from the University of Pisa. He contributes actively to the field as an associate editor of the European Economic Review, an international research fellow (ERSA, SARB), and a member of the Euro Area Business Cycle Dating Committee.