Lecture 1: Introduction (9/21)

• 
  

      Meanings of Identification

  
  


• 
  

      Reduced Form vs. Structural Model Identification

  
  

Lecture 2: Review for Linear Regression (9/28)               

• 
  

      Omitted Variable Bias

  
  


• 
  

      Practical Regression Hints

  
  


• 
  

      Krueger (1993) + DiNardo and Pischke (1997)

  
  

Lecture 3: Randomized Control Trials (10/5)

• 
  

      Counterfactual Framework

  
  


• 
  

      Regression and Causality

  
  


• 
  

      LaLonde (1986) + Smith and Todd (2005)

  
  

Lecture 4: Panel Data and Difference-in-Differences I (10/12)

• 
  

      Fixed Effect Estimation

  
  


• 
  

      Difference-in-Differences

  
  


• 
  

      Chu (2015) and Dickert-Conlin, Elder, and Moore (2011)

  
  

First Presentations (10/19) -- Topic

Lecture 5: Synthetic Control and Standard Errors I (10/26)

• 
  

      Synthetic Control Method

  
  


• 
  

      Standard Errors: How Should We View Uncertainty in DD Settings?

  
  

Problem Set 1

Lecture 6: Minimum Wage (11/2)

• 
  

      Standard Errors II        

  
  


• 
  

      Aaronson, French, Sorkin, and To (2018) + Meer and West (2015)

  
  

Lecture 7: Instrumental Variables (11/9)

• 
  

      IV and Simultaneous Equations           

  
  


• 
  

      IV and LATE

  
  


• 
  

      Angrist and Evans (1998): Labor Supply and Fertility

  
  

Lecture 8: Regression Discontinuity (Kink) Designs I (11/16)

• 
  

      Problem Set 1

  
  


• 
  

      Identifying Assumptions and Estimation

  
  


• 
  

      IV and RD

  
  

Mid-Term Presentations (11/23) -- Model and Data

Lecture 9: Regression Discontinuity (Kink) Design II (11/30)

• 
  

      Extrapolation of RD

  
  


• 
  

      Regression Kink Design

  
  


• 
  

      Unemployment Insurance

  
  

Lecture 10: Decomposition Methods in Economics (12/7)

• 
  

      Oaxaca-Blinder Decomposition

  
  


• 
  

      DFL Reweighting Method

  
  


• 
  

      Wage Density Decomposition

  
  

Problem Set 2

Lecture 11: Machine Learning and High-Dimensional Data (12/14)

• 
  

      Bias-Variance Decomposition

  
  


• 
  

      LASSO and Ridge Estimators

  
  


• 
  

      Generalized Synthetic Control

  
  

Lecture 12: Sufficient Statistic Approach for Welfare Analysis (12/21)

• 
  

      Basic Search Model

  
  


• 
  

      Optimal UI: Baily-Chetty Formula

  
  

Problem Set 3

Lecture 13: Sufficient Statistic Approach for Welfare Analysis (12/28)

• 
  

      Overconfidence and Optimal UI

  
  


• 
  

      Salience and Taxation

  
  

Final Presentations (1/4)

1. 40% Problem Sets 

We will do three problem sets during the course of semester. The problem set questions will include both theoretical questions and statistical analysis of data, which will involve the software package STATA (or R).

2. 60% Paper Proposal:

Each student is required to write a high-quality paper proposal. You should arrange to meet with me when you are ready to talk about a topic for your paper, and brief outlines (less than one page) of proposals are due by Novemeber 2. Final proposals are due on January 20.

Recommended Text for Labor Economics

Ashenfelter, Card, and Layard (eds.), The Handbook of Labor Economics, Volumes 4A.  http://www.sciencedirect.com/science/handbooks/15734463/4/part/PA

Dale T. Mortensen, Wage Dispersion: Why Are Similar Workers Paid Differently, The MIT Press 

Recommended Text for Econometrics:

Joshua D. Angrist and JÖrn-Steffen Pischke (2009), Mostly Harmless Econometrics, Princeton University Press 

Jeffrey Wooldridge (2010), Econometric Analysis of Cross Section and Panel Data, second edition. Cambridge, MA: MIT Press

Background Reading:

George Borjas, Labor Economics (6^th edition)

Jeffrey Wooldridge (2015), Introductory Econometrics: A Modern Approach (6th edition), Cengage