Creator |
|
|
|
|
Language |
|
Publisher |
|
|
Date |
|
Source Title |
|
Vol |
|
Issue |
|
First Page |
|
Last Page |
|
Publication Type |
|
Access Rights |
|
Crossref DOI |
|
Related DOI |
|
|
Related URI |
|
|
Relation |
|
|
Abstract |
Equivalence tests for binary data with pair-matched design in clinical trials are explored in this paper. Eight tests are considered altogether including those tests constructed by the GSK method, the... tests which use estimated null variances among others. The Type I error rates and powers are investigated by a Monte Carlo study, and it is shown that the test associated with the log-risk difference has the highest power among those eight tests. The determination of the value of tolerance is also discussed.show more
|