- Statist. Sci.
- Volume 32, Number 3 (2017), 349-351.
Randomization-Based Tests for “No Treatment Effects”
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.
Statist. Sci., Volume 32, Number 3 (2017), 349-351.
First available in Project Euclid: 1 September 2017
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Chung, EunYi. Randomization-Based Tests for “No Treatment Effects”. Statist. Sci. 32 (2017), no. 3, 349--351. doi:10.1214/16-STS590. https://projecteuclid.org/euclid.ss/1504253118
- Main article: A Paradox from Randomization-Based Causal Inference.