CEMFI SUMMER SCHOOL

Description

CEMFI
CEMFI SUMMER SCHOOL
22 August - 16 September 2022, Madrid, Spain

CEMFI SUMMER SCHOOL offers top-level training for practitioners, central bankers, and academics. Participants are exposed to the latest developments in each field. Courses are taught within a five-day period and provide an intensive, rigorous, and in-depth analysis of the topics covered. In 2022 some courses will take place in person and others will be online.

CEMFI is an independent non-profit foundation created by the Bank of Spain. CEMFI’s faculty is committed to high-quality research and faculty members publish in the most prestigious international academic journals. Moreover, CEMFI is widely known for its excellence in teaching.

COURSES:

CAUSAL INFERENCE FOR HEALTH AND SOCIAL SCIENTISTS
22 - 26 August 2022 (09:30 to 13:00 CEST, onsite)

Miguel Hernán (Harvard University)

The course introduces a general-purpose causal inference framework that integrates methods for both experimental and non-experimental data. The framework has two steps: 1) specification of the (hypothetical) target experiment or trial that would answer the causal question of interest, and 2) emulation of the target trial using the available data. The course explores key challenges for target trial emulation and critically reviews methods proposed to overcome those challenges. The methods are presented in the context of the evaluation of the comparative effectiveness of health interventions using existing databases of administrative and clinical data.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=10&q=SSR

LOCAL PROJECTION METHODS FOR TIME SERIES AND PANEL DATA
22 - 26 August 2022 (09:30 to 13:00 CEST, onsite)

Óscar Jordà (Federal Reserve Bank of San Francisco)
A convenient way to estimate how a variable responds to a given intervention over time is with the method of local projections. A local projection is a regression of an outcome variable observed in the future, on an intervention variable today, conditional on controls observed today or earlier. In linear settings, this simple approach results in estimates of impulse responses that are asymptotically equivalent to those obtained from vector autoregressions (VAR) under standard regularity assumptions. However, because local projections rely on single equation methods, they have quickly become a popular tool in large dimensional, longitudinal, and nonlinear data settings. Moreover, local projections provide a natural nexus with the policy evaluation literature in applied microeconomics. This opens up interesting complementarities.

The goal of the course is to briefly discuss VAR-based methods, including Bayesian estimation, and quickly pivot to discuss local projections. We will explore the basic statistical properties of current estimators and inferential methods before moving on to issues of identification. These include basic control (such as inverse propensity score weighting), and instrumental variable approaches. Next, we will tackle the issue of decomposing the impulse response into its constituent components using the Kitagawa-Oaxaca-Blinder decomposition. This decomposition will allow us to investigate nonlinearities and time-varying extensions that are nevertheless linear in the parameters and therefore estimable by standard least-squares methods. Finally, we investigate panel data applications. In particular, we analyze situations where identification is achieved using difference-in-differences settings.

The breadth of topics covered limit the rigor with which each result will be discussed, though appropriate references will be provided for those interested. The goal of the course is to guide practitioners to appropriate methods for their problems, and to elicit fruitful extensions and avenues for new research.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=11&q=SSR

EMPIRICAL ANALYSIS OF FIRM PERFORMANCE
22 - 26 August 2022 (09:30 to 13:00 CEST, onsite)

Jan de Loecker (KU Leuven)

The objective of this course is to introduce the main questions and methodologies in the analysis of firm performance from the point of view of the Industrial Organization literature. Participants will learn how to critically evaluate empirical work in Industrial Organization, and related fields studying firm performance (such as trade, macro, and development economics) and develop tools for research. The empirical work covered will typically have a close tie to a theoretical model. The basic structure of the course will involve presentation and discussion of papers that should be read in advance. Problem sets will be made available to implement the estimation routines and analysis presented during the lectures..
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=12&q=SSR

NEW DEVELOPMENTS IN THE ECONOMETRICS OF HETEROGENEOUS WORKERS AND FIRMS
22 - 26 August 2022 (15:30 to 19:00 CEST, onsite)

Elena Manresa (New York University)

In recent years there has been an upsurge of interest in new methods for the analysis of matched employer-employee data to study the labor market, partly motivated by the increasing availability of this type of datasets. Existing methods are also finding applicability in other areas such as international trade, economic geography, environmental economics or intergenerational mobility. A main theme is how to deal with multiple heterogeneities and their potential interactions. This course will introduce newly developed approaches to deal with unobserved heterogeneity in conventional and matched panel data sets with an emphasis on discrete-classification methods. It will also provide an overview of traditional methods to decompose earnings variability into worker and firm-level effects as well as the more recent distributional approaches. Finally, the course will review methods for studying transitions and dynamic responses.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=13&q=SSR

ADVANCED NUMERICAL METHODS IN MACROECONOMICS
29 August - 2 September 2022 (15:30 to 18:30 CEST, online)

Jesús Fernandez-Villaverde (University of Pennsylvania) and Galo Nuño (Banco de España)

Since the financial crisis one decade ago, macroeconomics has made tremendous advances in incorporating nonlinear phenomena (such as sovereign or banking crises) and non-trivial heterogeneity in households and firms into dynamic general equilibrium models. These advances have, in turn, pushed the boundaries in numerical methods able to solve efficiently nonlinear models. The switch from discrete to continuous time methods in the formulation of macro models, the introduction of machine learning techniques -particularly deep learning- in the solution of these models, and the adoption of parallelization techniques to speed up computations are three of the more relevant developments, with far reaching consequences in the type of problems that macroeconomist can study. In this course we discuss these recent advances, providing students with the necessary tools to apply them to their research agendas, as well as including relevant examples in topics such as monetary policy or financial stability.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=14&q=SSR

FIRM DYNAMICS AND ECONOMIC GROWTH
29 August - 2 September 2022 (09:30 to 13:00 CEST, onsite)

Ufuk Akcigit (University of Chicago)

This course focuses on the theory and empirics of economic growth. The class will follow a micro-to-macro approach and hence special emphasis will be given to firms and inventors to uncover the determinants of aggregate productivity growth. In addition to some classic papers, the class will mainly focus on recent research. Students will be encouraged to discuss the frontier topics in class and produce new and exciting research ideas.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=15&q=SSR

THE MACROECONOMICS OF CENTRAL BANK DIGITAL CURRENCIES (CBDCs)
29 August - 2 September 2022 (15:30 to 19:00 CEST, onsite)

Dirk Niepelt (University of Bern)

Central banks across the world consider the introduction of retail central bank digital currency (CBDC), a central bank liability in digital form that households and firms may use as a payment instrument. The objective of the course is to familiarize participants with macroeconomic perspectives on the potential costs and benefits of CBDC. We start with an overview of central bank activities and motivations before turning to models of how CBDC affects bank intermediation, payments, capital accumulation and other macroeconomic outcomes. We also touch upon political economy and implementation issues.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=16&q=SSR

UNUSTRUCTURED DATA IN EMPIRICAL ECONOMICS
5 - 9 September 2022 (15:30 to 18:30 CEST, online)

James H. Stock (Harvard University)

Over the past decade, the use of unstructured data has been growing steadily in economics and related disciplines, with a rapid acceleration in the wake of COVID-19. This course will begin with an overview of types of unstructured data and recent applications. We will then cover the basics of processing and filtering such data to produce reliable measurements of economic phenomena.

One of the key properties of many unstructured datasets is the vast number of features available for each observation. The remainder of the course will introduce strategies for exploiting this richness, most of which come from the machine learning (ML) literature.

We will first introduce “off-the-shelf” ML methods that empirical economists have productively used in recent research, including matrix factorization, word embeddings, and topic models. The motivating examples for these methods will largely come from text data but we will also discuss other applications including survey data.
The course will conclude by introducing methods for building and estimating new models that link unstructured data to the economic environment of interest more closely than is possible with off-the-shelf models. This will draw on recently introduced probabilistic programming languages that make feasible complex inference problems.
The core ideas from lectures will be complemented by hands-on classes during which students will work through the application of the above techniques to actual datasets
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=17&q=SSR

PANEL DATA ECONOMETRICS
12 - 16 September 2022 (09:30 to 13:00 CEST, onsite)

Steve Bond (Oxford University)

The purpose of this course is to provide an up-to-date coverage of the main methods and models used in the econometric analysis of panel data, with particular focus on panels where the cross-sectional dimension is large and the time-series dimension is short. The course will cover applications to production functions, investment models, empirical growth models, and the implementation of panel GMM estimators using Stata (xtabond2).
The course will combine pre-recorded lectures, live lectures, and classes. The live lectures will mainly be used to demonstrate how to implement methods in Stata. Exercises will be assigned for participants to do in Stata. The course will be complemented with extensive office hours.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=18&q=SSR

MACHINE LEARNING IN FINANCE
12 - 16 September 2022 (09:30 to 13:00 CEST, onsite)

Ansgar Walther (Imperial College)

This course shows how to apply modern statistical techniques to big financial data. The focus is on how machine learning can guide academic research in Finance, as well as decisions in the financial industry, including asset managers, hedge funds, and consumer finance companies. We will cover unsupervised and supervised machine learning techniques and their applications in asset pricing and credit scoring. We will also cover reinforcement learning, with applications to portfolio choice. The primary purpose of this course is not only to teach statistical methods, but also to facilitate the financial and economic interpretation of machine learning. Hence, we will pay special attention to the interpretability of machine-learning results, and to the distinction between correlation and causation.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=19&q=SSR

DESIGNING EXPERIMENTS IN COMPLEX SYSTEMS: SPILLOVER, STRATEGIC, AND EQUILIBRIUM EFFECTS
12 - 16 September 2022 (15:30 to 19:00 CEST, onsite)

Stefan Wager (Stanford University)

Randomized controlled trials are typically studied under a “no interference” assumption, whereby the treatment given to one experimental unit does not affect outcomes for others. In recent years, however, there has been considerable interest in running experiments in complex systems where cross-unit interactions not only exist, but are of central importance. Examples of such settings include community-level interventions in development economics, and interventions that affect production/consumption decisions of participants in a marketplaces or online platform. This series of lectures will survey recent advances in experimental design under cross-unit interference, with special emphasis on settings where interference can be captured via economic modeling.
https://www.cemfi.es/programs/css/landing_campaign.asp?cu=20&q=SSR

MORE INFORMATION AND ONLINE APPLICATIONS:
https://www.cemfi.es/programs/css/index.asphttps://www.cemfi.es/programs/css/landing_campaign.asp?cu=00&q=SSR
EMAIL: css@cemfi.es