Conditional Inference for Restricted Randomization Designs

Publication Description
In a clinical trial to compare two treatments, suppose that patients are assigned to treatment according to a certain class of restricted randomization rules. Conditional on the difference in numbers between the two treatment groups, the asymptotic null distribution of a class of permutation tests is shown to be Gaussian.

Primary Author
R. T. Smythe

Volume
16

Issue
3

Start Page
1155

Other Pages
1161

Publisher
Institute of Mathematical Statistics

URL
https://www.jstor.org/stable/2241623



Reference Type
Journal Article

Periodical Full
The Annals of Statistics

Publication Year
1988

Publication Date
Sep 1,

ISSN/ISBN
0090-5364

Document Object Index
10.1214/aos/1176350952