Return to Homepage    

Publications

1. When Can We Ignore the Measurement Error in the Running Variable? (with Michal Kolesá),  Journal of Applied Econometrics, 2023, http://doi.org/10.1002/jae.2974

2. Regression Discontinuity Designs with a Continous Treatment, 2021, Journal of the American Statistical Association (with Ying-Ying Lee and Michael Gou) (Stata code, R code).

3. Regression Discontinuity Designs with Sample Selection,  Journal of Business and Economic Statistics, 2019, 37 (1), 171-185.(Presentation Slides).

4. Alternative Assumptions to Identify LATE in Fuzzy Regression Discontinuity Designs, Oxford Bulletin of Economics and Statistics, 2018, 80 (5). 1020-1027 (Online Appendix, a longer version, Presentation Slides).

5. Testing for Rank Invariance or Similarity in Program Evaluation, The Review of Economics and Statistics, 2018, 100 (1), 78-85 (with Shu Shen, Online Appendices, a longer version, Presentation Slides, data and code).

6. Mandatory Retirement and the Consumption Puzzle: Disentangling Price and Quantity Declines, 2017, Economic Inquiry, 55(4), 1738-58 (with Dennis Yang, Online Appendices).

7. Testing Stability of Regression Discontinuity Models, with Giovanni Cerulli, Arthur Lewbel, and Alexander Poulsen, Advances in Econometrics, 2017, 38, 317-339, in M. Cattaneo , J. C. Escanciano (ed.) Stata module: TED .

8. Identifying the Effect of Changing the Policy Threshold in Regression Discontinuity Models, (Supplemental Online Appendix, Presentation Slides, with Arthur Lewbel, The Review of Economics and Statistics, 2015, 97(5), 1081-1092

9. Regression Discontinuity Applications with Rounding Errors in the Running Variable, (Supplemental Online Appendix, Presentation Slides), Journal of Applied Econometrics, 2015, 30(3), 422-446.

This paper proposes a bias correction formula for the estimated RD LATE. The standard errors for the bias corrected estimate are then obtianed by the Delta method. Alternatively, one can directly bias-correct the polynomial regression terms before estimation, which allows for obtianing the standard errors directly. For this conveneint alternative approach, please see the Online Appendix I to my empirical paper.

10. A Simple Estimator for Binary Choice Models with Endogenous Regressors, Econometric Reviews, 34(1-2), 82-105. (with Arthur Lewbel, Stata module sspecialreg)  

11. How Health Insurance Affects Health Care Demand - A Structural Analysis of Behavioral Moral Hazard and Adverse Selection, Economic Inquiry, 2013, 51(2), 1324-44.

12. Comparing Features of Convenient Estimators for Binary Choice Models With Endogenous Regressors, (with Arthur Lewbel and Thomas Tao Yang) , Canadian Journal of Economics, 2012, 45(3), 809-829.

13. Nonparametric Identification of a Binary Random Factor in Cross Section Data, (with Arthur Lewbel), Journal of Econometrics, 2011, 163(2), 163-171. A longer version with supplemental material

14. Semiparametric Binary Random Effects Models: Estimating Two Types of Drinking Behavior, Economics Letters, 2011, 112(1), 79-81.

15. Kept Back to Get Ahead?  Kindergarten Retention and Academic Performance, European Economic Review, 2010, 54 (2), 219-236.

16. Endogenous Regressor Binary Choice Models Without Instruments, With an Application to Migration, Economics Letters, 2010, 107(1), 33-35. A longer version and the supplemental material

Working Papers

1. Nonparametric Doubly Robust Identification of Causal Effects of a Continuous Treatment using Discrete Instruments (with Ying-Ying Lee)

2. Jump or Kink? Regression Probability Jump and Kink Design for Treatment Effect Evaluation