Logotipo NIPE
NIPE SUMMER SCHOOL | 20thEdition

DIFFERENCE-IN-DIFFERENCES AND EVENT STUDIES FOR PANEL DATA AND REPEATED CROSS SECTIONS

with Jeffrey M. Wooldridge

15 TO 18 JULY 2024
UNIVERSITY OF MINHO | BRAGA – PORTUGAL

Instruction

Jeffrey M. Wooldridge is University Distinguished Professor of Economics and Walter Adams Distinguished Faculty Fellow in Economics at Michigan State University, where he has taught since 1991. He previously taught at MIT. He received his bachelor of arts, with majors in computer science and economics, from the University of California, Berkeley, and his doctorate in economics from the University of California, San Diego. Dr. Wooldridge is a fellow of the Econometric Society and of the Journal of Econometrics, and is a founding fellow of the International Association for Applied Econometrics. His other awards include the Distinguished Author award from the Journal of Applied Econometrics, the Plura Scripset award from Econometric Theory, and the Sir Richard Stone prize from the Journal of Applied Econometrics. He has also served on several editorial boards, including as editor of the Journal of Business and Economic Statistics. Dr. Wooldridge has written chapters for the Handbook of Econometrics and the Handbook of Applied Econometrics. He is the author of of the textbooks Introductory Econometrics: A Modern Approach (South-Western, 7e, 2019) and Econometric Analysis of Cross Section and Panel Data (MIT Press, 2e, 2010).

Course Outline and Software

Course outline

We will cover difference-in-differences and event study methods for policy analysis, with an emphasis on panel data. However, I will also discuss how flexible regression methods apply to repeated cross sections. We will begin with flexible regression-based methods, including two-way fixed effects estimation of a flexible equation allowing for staggered interventions and heterogeneous treatment effects. Imputation methods and doubly robust methods based on rolling estimation (including long differencing) also will be covered.

I will make connections between standard difference-in-differences estimators and event-study estimators, including how to make event-study methods more flexibly by controlling for covariates in order to relax the parallel trends assumption. We will discuss how to test for pre-trends and how to adjust for heterogeneous trends.

Other topics include modifications required if there is no never treated group, how to allow for exit from treatment, how to handle unbalanced panels, and issues that arise with time-varying control variables. We will also learn how one can obtain inference in situations with a small number of cross-sectional units, as well as provide an overview of synthetic control methods.

We will briefly cover extension of regression-based methods to non-binary treatments. I will show how linear regression methods extend to nonlinear difference-in-differences methods for binary, fractional, and nonnegative (including count and corner solution) outcomes. The final topic shows how methods for panel data can be modified for repeated cross sections.

Laboratory/practical sessions will be taught using Stata, and participants are expected to bring their laptops.
Temporary licenses will be freely provided to participants during the summer school.

Program

DAY 1

Session 1: 9:15-10:30

Introduction and Overview; Two-Period Panel Data Case; No Anticipation and Parallel Trends; Regression Adjustment and Propensity Score Methods

Coffee Break: 10:30-10:45

Session 2: 10:45-12:00

General Common Intervention Timing; Pooled OLS and Extended Controlling for Covariates via Regression Adjustment; Event Study Estimation

Lunch Break: 12:00-13:30

Session 3: 13:30-14:45

Staggered Interventions, I; Heterogeneous Effects; Imputation; Pooled OLS and Extended TWFE; All Units Eventually Treated

Coffee Break: 14:45-15:00

Practical Session: 15:00-16:30

 

DAY 2

Session 4: 9:15-10:30

Staggered Interventions, II. Strategies with Exit. Event Study Methods. Testing and Correcting for Violation of Parallel Trends.

Coffee Break: 10:30-10:45

Session 5: 10:45-12:00

Staggered Interventions, III; Alternative Imputation Estimators; Rolling Methods and Long Differencing; Propensity Score Methods. 

Lunch Break: 12:00-13:30 

Session 6: 13:30-14:45

Small Number of Cross-Sectional Units; Synthetic Control Methods

Coffee Break: 14:45-15:00

Practical Session: 15:00-16:30

 

DAY 3

Session 7: 9:15-10:30

Non-Binary Treatments; Time-Varying Covariates; Unbalanced Panels; Standard Errors

Coffee Break: 10:30-10:45 

Session 8: 10:45-12:00

Nonlinear DiD. Binary, Fractional, and Nonnegative Reponses; Quasi-MLE Estimation

Lunch Break: 12:00-13:30

Session 9: 13:30-14:45

Difference-in-Differences with Repeated Cross Sections

 

DAY 4

Research Seminar: “Estimating Distributional Treatment Effects with Staggered Interventions for Panel Data”

Entry Requirements

A graduate degree (MSc or PhD) in Economics, Management, Finance, Mathematics, Statistics, or closely related fields. We also welcome applications from qualified MSc students in these fields.

Please note that ECTS credits are not issued for this summer school.

Registration and Fees

CV Upload

Registration type

Students need to provide a letter from their advisor confirming their student status.

We will reply to your message with instructions on how to proceed with the payment of the registration fee.

NIPE/EEG informs that photographs and/or video will be taken at this event for academic activity reporting purposes.
Personal data treatment and privacy policy

Registration in the summer school by qualified applicants is accepted on a rolling basis, meaning that the registration will close once it reaches the maximum intake of 40 participants.

Early registration: 650€ Late registration: 800€
Students* (PhD, Master) early registration: 500€ Students* (PhD, Master) late registration: 650€

 

* Students need to provide a letter from their advisor confirming their student status;
The application deadline is June 30th, 2024; The early-bird discount applies to payments made on or before June 3rd, 2024.
A cancellation fee of 100 EUR is charged for cancellations until July 5th, 2024. No reimbursements will be made for cancellations after this date.
Fees cover attendance, lunches and two refreshments from Monday to Wednesday (July 15–17), and a bus pass (provided upon registration) which allows you to use Braga’s public transport (TUB) at no cost during the summer school.

Organizing Team

Luís Sá

E-mail: luis.sa@eeg.uminho.pt

Nelson Areal 

E-mail: nareal@eeg.uminho.pt

Susana Figueiredo 

E-mail: nipe.summerschool@eeg.uminho.pt
Phone: +351 253 604 518

Pratical Information

The summer school will take place at the School of Economics and Management, University of Minho, Braga, Portugal. EEG-UMinho was founded on 10 March 1982. It is an organic unit of education, research and interaction with society.

It focus on activities ranging from the sciences of economics to business administration and political science and international relations, and other related areas. It offers 8 Bachelor Programmes, 14 Master Programmes and 5 PhD Programmes, accounting for approximately 2500 students. The School is widely recognised for the quality of its research: it integrates 2 Research Units, one of which achieved a maximum rating of “Excellent” by the Portuguese Foundation for Science and Technology (FCT).

The closest airport to Braga is Francisco Sá Carneiro Airport, in Porto, which stands some 45 Km away from Braga. For GPS users, the coordinates to UMinho are (according to Google Earth): 41°33’41.00″N and 8°23’54.45″W.

The easiest way to get to Braga is by using the “get Bus”, which does daily transfers from the Francisco Sá Carneiro Airport to Braga.

Note that as an alternative, you can take the subway, Line Violeta to Campanhã Station [about 33 minutes, between 6am and 1:30am]. From there you should get the train to Braga. Information on train prices and timetables can be found in the CP website. Braga train station is 5 minutes walking distance from the city centre.

From Porto airport to Braga participants can also:

  • rent a car
  • take a taxi
  • a bus service is also available from downtown Porto (Rua Alfredo Magalhaes)

These are the hotels with which we negotiated special prices for Summer School participants.

*****
SINGLE
DOUBLE
LOCATION Near University (5 min walking distance)
NOTES
Reservations: res.melia.braga@meliaportugal.com
****
SINGLE
DOUBLE
LOCATION City centre
NOTES
***
SINGLE
DOUBLE
LOCATION City centre
NOTES
****
Hotel do Parque, Hotel do Elevador
and Hotel do Templo
SINGLE
DOUBLE
LOCATION Bom Jesus
Mountain
(10 min by car)
NOTES
***
Hotel do Lago and Hotel João Paulo II
SINGLE
DOUBLE
LOCATION Bom Jesus
Mountain
(10 min by car)
NOTES
***
SINGLE €-
DOUBLE €-
LOCATION Near University (10 min walking distance)
NOTES
***
SINGLE
DOUBLE
LOCATION  Braga train station (buses running to and from the university of Minho every 15 minutes).
NOTES
Reservations: www.axishoteis.com

 

SINGLE
DOUBLE
LOCATION City centre
NOTES
SINGLE €-
DOUBLE €-
LOCATION City centre
NOTES

Previous Editions

Manuel Arellano

17th NIPE Summer School

Econometrics of Survey Data, Stratification, and Clustering

Princeton University.

Matias D. Cattaneo

16th NIPE Summer School

Regression Discontinuity Designs

Princeton University

Badi H. Baltagi

15th NIPE Summer School

Panel Data Spatial Econometrics

Syracuse University

Roger Koenker

14th NIPE Summer School

Advances in Quantile Regression

University of Illinois

Yacine Ait-Sahalia

13th NIPE Summer School

An Introduction to High Frequency Financial Econometrics and Trading

Universidade de Princeton, EUA

Francis X. Diebold

12th NIPE Summer School

New Directions in Macro-Econometric and Financial-Econometric Predictive Modeling

Universidade da Pensilvânia, EUA

Stephen Brown

11th NIPE Summer School

Empirical Financial Economics

New York University, EUA

William Greene

10th NIPE Summer School

Discrete choice models for cross section and panel data

Universidade de Nova Iorque, EUA

Paul Levine and Bo Yang

9th NIPE Summer School

The Science and Art of DSGE Modelling: A Course on Model Construction, Calibration, Estimation and Policy Analysis

Universitu of Surrey
London Metropolitan University and University of Surrey

Nicholas M. Kiefer

8th NIPE Summer School

Duration Analysis

Cornell University

Colin Cameron

7th NIPE Summer School

Regression Analysis with Discrete and Censored Dependent Variables

University of California – Davis

Joshua Angrist

6th NIPE Summer School

Empirical Strategies

MTI

James Hamilton

5th NIPE Summer School

Bayesian Econometrics

University of California, San Diego, EUA

Ellen McGrattan

4th NIPE Summer School

Quantitative Methods in Macroeconomics and Policy Analysis

University of Minnesota and Federal Reserve Bank of Minneapolis, USA

Jeffrey M. Wooldridge

3rd NIPE Summer School

Topics in Program Evaluation

Michigan State University, USA

Frank Windmeijer

2nd NIPE Summer School

Dynamic Panel Data Analysis

Institute for Fiscal Studies, London

Paul Schweinzer

1st NIPE Summer School

Mathematics for Economists

Birkbeck College – London