NATIONAL BUREAU OF ECONOMIC RESEARCH
NATIONAL BUREAU OF ECONOMIC RESEARCH

Using Split Samples to Improve Inference about Causal Effects

Marcel Fafchamps, Julien Labonne

NBER Working Paper No. 21842
Issued in January 2016
NBER Program(s):Development Economics

We discuss a method aimed at reducing the risk that spurious results are published. Researchers send their datasets to an independent third party who randomly generates training and testing samples. Researchers perform their analysis on the former and once the paper is accepted for publication the method is applied to the latter and it is those results that are published. Simulations indicate that, under empirically relevant settings, the proposed method significantly reduces type I error and delivers adequate power. The method – that can be combined with pre-analysis plans – reduces the risk that relevant hypotheses are left untested.

download in pdf format
   (330 K)

email paper

Machine-readable bibliographic record - MARC, RIS, BibTeX

Document Object Identifier (DOI): 10.3386/w21842

Users who downloaded this paper also downloaded* these:
List, Shaikh, and Xu w21875 Multiple Hypothesis Testing in Experimental Economics
Anderson and Magruder w23544 Split-Sample Strategies for Avoiding False Discoveries
Coase Industrial Organization: A Proposal for Research
Scitovsky A Survey of Some Theories of Income Distribution
Rajan and Subramanian w11513 Aid and Growth: What Does the Cross-Country Evidence Really Show?
 
Publications
Activities
Meetings
NBER Videos
Themes
Data
People
About

National Bureau of Economic Research, 1050 Massachusetts Ave., Cambridge, MA 02138; 617-868-3900; email: info@nber.org

Contact Us