Abstract
We consider the problem of accounting for multiplicity for two correlated endpoints in the comparison of two treatments using weighted hypothesis tests. Various weighted testing procedures are reviewed, and a more powerful method (a variant of the weighted Simes test) is evaluated for the general bivariate normal case and for a particular clinical trial example. Results from these evaluations are summarized and indicate that the weighted methods perform in a manner similar to unweighted methods.
Original language | English |
---|---|
Pages (from-to) | 7-13 |
Number of pages | 7 |
Journal | Pharmaceutical Statistics |
Volume | 4 |
Issue number | 1 |
DOIs | |
State | Published - Jan 2005 |
Keywords
- Hypothesis test
- Multiplicity
- Weighted multiple comparison