Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/211113
Authors: 
Carneiro, Pedro M.
Lee, Sokbae
Wilhelm, Daniel
Year of Publication: 
2019
Series/Report no.: 
cemmap working paper No. CWP21/19
Abstract: 
In a randomized control trial, the precision of an average treatment effect estimator and the power of the corresponding t-test can be improved either by collecting data on additional individuals, or by collecting additional covariates that predict the outcome variable. To design the experiment, a researcher needs to solve this tradeoff subject to her budget constraint. We show that this optimization problem is equivalent to optimally predicting outcomes by the covariates, which in turn can be solved using existing machine learning techniques using pre-experimental data such as other similar studies, a census, or a household survey. In two empirical applications, we show that our procedure can lead to reductions of up to 58% in the costs of data collection, or improvements of the same magnitude in the precision of the treatment effect estimator.
Document Type: 
Working Paper

Files in This Item:
File
Size
506.34 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.