General Reading
(i) The main reading is Chapter 25 of Cameron and Trivedi's "Microeconometrics".
(ii) The Blundell and Costas-Dias paper is a very good companion.
(iii) The book "Mostly Harmless Econometrics" is also a very good paper for understanding the evaluation of treatment effects. (chapters 2, 4, 5 and 6 particularly useful)
(iv) Angus Deaton's 2010 paper is a very good paper for discussing the limitations of IV and randomised controlled trials.
Deaton, Angus. 2010. "Instruments, Randomization, and Learning about Development." Journal of Economic Literature, 48(2): 424-55.
Natural Experiments: Regression Discontinuity and Diff-in-Diff
(v) As a very strong example of the regression discontinuity design, below is a paper by Angrist and Lavy.
"Angrist, J. and V. Lavy “Using Maimonodes Rule to Estimate the Effect of Class Size on Scholastic Achievement” Quarterly Journal of Economics, 114, 533-575 "
(vi) Duflo's (2001) paper is a very good example of the a Differences-in-Differences analysis. (attached)
Esther Duflo, 2001. "Schooling and Labor Market Consequences of School Construction in Indonesia: Evidence from an Unusual Policy Experiment," American Economic Review, American Economic Association, vol. 91(4), pages 795-813, September.
Randomised Controlled Trials
(vii) Two main application papers for class are below:
Miguel, E. and Kremer, M. (2004), Worms: Identifying Impacts on Education and Health in the Presence of Treatment Externalities. Econometrica, 72: 159–217. doi: 10.1111/j.1468-0262.2004.
Esther Duflo and Emmanuel Saez" The Role of Information and Social Interactions in Retirement Plan Decisions: Evidence from a Randomized Experiment" The Quarterly Journal of Economics (2003) 118(3): 815-842 doi:10.1162/00335530360698432
(vii) Simple paper about field experiments by John List below:
(viii) John List and Imran Rasul 2011 Handbook of Labour Economics chapter very good also. Not compulsory reading but it would be good to read, in particular, the first few sections to understand how field experiments are being used.
No comments:
Post a Comment