Previous Training Courses
This course will cover several methods for estimating causal effects with an emphasis on methods that can be used to analyze policy interventions. For cross-sectional data we consider cases where the assignment is randomized; randomized conditional on observed covariates; and where assignment depends fundamentally on unobservables. In addition to instrumental variables methods this course will cover control function methods that allow estimation of a variety of causal effects. The basics of regression discontinuity designs, which can be used to exploit institutional features of program participation, will also be discussed.
General difference-in-differences (DID), including allowing for multiple treatment groups and time periods, with different pre-treatment trends, will also be covered. There will also be some discussion of nonlinear DID. The final topic is policy analysis with panel data. Throughout the course, Professor Wooldridge will mention certain issues in obtaining valid standard errors and confidence intervals.
October 25-26, 2018
Robert Miller-Carnegie Mellon University
Identifying and Estimating Dynamic Discrete Choice Models
This course develops structural approaches for analyzing large cross sectional and longitudinal data sets, by exploiting restrictions derived from the equilibrium dynamic outcomes in individual discrete choice optimization problems and non-cooperative games. We investigate empirical content, characterize identification of the primitives and counterfactuals, and evaluate alternative estimators and testing procedures.
The course will provide an introduction to standard and recent methodological developments in program evaluation, with particular focus on (reduced form) treatment effect estimation and inference in experimental and observational settings. It will focus on methodology and empirical practice, and will not discuss much of the statistical and econometric theory underlying the results.
May 21-22, 2018
Jeffrey M. Wooldridge-Michigan State University
Panel Data Econometrics
This course in panel data econometrics, presented primarily from a microeconometrics perspective, will cover linear panel data models with unobserved heterogeneity, including discussions of the strengths and weakness of the various estimation methods. Basic estimation methods include random effects, fixed effects, and first differencing. Instrumental variables estimation of models without strictly exogenous explanatory variables will also be covered, including those that contain contemporaneously endogenous variables and those that contain lagged dependent variables. Estimation of linear models with heterogeneous trends and heterogeneous slopes will also be covered. Special considerations with unbalanced panels will be discussed, including how to test for sample selection and attrition bias. The statistical package Stata will be used to illustrate the methods during lectures and in obtaining hands-on experience.
June 26-27, 2017
Kai-Uwe Kuhn-University of East Anglia
Regulating the Internet Economy: Policy Issues and Economic Analysis
The course starts with a brief overview of the way in which the internet economy has been “disruptive” to traditional ways of doing business and the regulatory concerns that have resulted – especially in Europe. It then briefly introduces some fundamental economic concepts of complementarity and coordination that are important to understanding innovation processes in the internet economy and the particular business practices that are emerging. These tool are used to analyse the issues of potential dominance of platforms like Google, Amazon, or Facebook that has raised concerns in the policy debates (especially in Europe) on the basis of a number of competition cases. In the second half of the course we look in more detail at the regulatory issues in platform markets, in particular discussions surrounding the use of data, the role of pricing algorithms for competition, as well as issues for consumer and worker protection that arise from novel business formats in the internet economy.
This course introduces students to modern methods for conducting and analyzing surveys. The first day will focus on designing survey questions and approaches to sampling and interviewing respondents. The second day will focus on analyzing survey responses, paying special attention to techniques that are needed to deal with the inevitably substantial non-response that challenges most contemporary surveys.
The goal of this short course is to give an introduction to standard and recent methodological developments in program evaluation, with particular focus on (reduced form) treatment effect estimation and inference in experimental and observational settings. It focuses on methodology and empirical practice, and will not discuss much of the statistical and econometric theory underlying the results.
May 12-13, 2016
William Greene – New York University
Discrete Choice Models
April 27-28, 2016
Matias Cattaneo– University of Michigan
August 20-21, 2015
William Greene – New York University
Discrete Choice Modeling
June 17-18, 2015
Francis Vella – Georgetown University
May 7-8, 2015
David Drukker – State Corporation
Implementing Econometric Estimators in Stata