Open Access
August 2017 Randomization-Based Tests for “No Treatment Effects”
EunYi Chung
Statist. Sci. 32(3): 349-351 (August 2017). DOI: 10.1214/16-STS590


Although both Fisher’s and Neyman’s tests are for testing “no treatment effects,” they both test fundamentally different null hypotheses. While Neyman’s null concerns the average casual effect, Fisher’s null focuses on the individual causal effect. When conducting a test, researchers need to understand what is really being tested and what underlying assumptions are being made. If these fundamental issues are not fully appreciated, dubious conclusions regarding causal effects can be made.


Download Citation

EunYi Chung. "Randomization-Based Tests for “No Treatment Effects”." Statist. Sci. 32 (3) 349 - 351, August 2017.


Published: August 2017
First available in Project Euclid: 1 September 2017

zbMATH: 06870247
MathSciNet: MR3695997
Digital Object Identifier: 10.1214/16-STS590

Keywords: Fisher’s randomization test , Neyman’s randomization test , treatment effect , Wilcoxon–Mann–Whitney rank sum test

Rights: Copyright © 2017 Institute of Mathematical Statistics

Vol.32 • No. 3 • August 2017
Back to Top