A Theory of Experimenters: Robustness, Randomization, and Balance
作者: Abhijit V. BanerjeeSylvain ChassangSergio MonteroErik Snowberg
作者单位: 1Department of Economics, Massachusetts Institute of Technology (email: banerjee@mit.edu )
2 Department of Economics, New York University (email: chassang@nyu.edu )
3 Department of Political Science, University of Rochester (email: smontero@rochester.edu )
4 Vancouver School of Economics, University of British Columbia (email: snowberg@mail.ubc.ca )
刊名: American Economic Review, 2020, Vol.110 (4), pp.1206-1230
来源数据库: American Economic Association
DOI: 10.1257/aer.20171634
原始语种摘要: This paper studies the problem of experiment design by an ambiguity-averse decision-maker who trades off subjective expected performance against robust performance guarantees. This framework accounts for real-world experimenters’ preference for randomization. It also clarifies the circumstances in which randomization is optimal: when the available sample size is large and robustness is an important concern. We apply our model to shed light on the practice of rerandomization, used to improve balance across treatment and control groups. We show that rerandomization creates a trade-off between subjective performance and robust performance guarantees. However, robust performance guarantees diminish very slowly with the number of rerandomizations. This suggests that moderate levels of...
全文获取路径: 美国经济学会 

  • trades 信风
  • robustness 坚固性
  • subjective 舟的
  • quantile 分位数
  • averse 嫌恶的
  • expected 预期
  • guarantees 抵押品
  • optimal 最佳的
  • balance 平衡
  • decision 决定