Abstract
In this article, we consider the problem of constructing simultaneous confidence intervals for odds ratios in 2 × k classification tables with a fixed reference level. We discuss six methods designed to control the familywise error rate and investigate these methods in terms of simultaneous coverage probability and mean interval length. We illustrate the importance and the implementation of these methods using two {\sc hiv} public health studies.
Acknowledgment
We would like to thank the Associate Editor and the two anonymous referees for their constructive comments on an earlier version of this manuscript.
Notes
*B: Bonferroni, SI: [Sbreve]idák, SC: Scheffé, D: Dunnett, HW: Hunter–Worsley, ME: McCann–Edwards.
†B: Bonferroni, SI: [Sbreve]idák, SC: Scheffé, D: Dunnett, HW: Hunter–Worsley, ME: McCann–Edwards.
‡B: Bonferroni, SI: [Sbreve]idák, SC: Scheffé, D: Dunnett, HW: Hunter–Worsley, ME: McCann–Edwards.
§B: Bonferroni, SI: [Sbreve]idák, SC: Scheffé, D: Dunnett, HW: Hunter–Worsley, ME: McCann–Edwards.
¶B: Bonferroni, SI: [Sbreve]idák, SC: Scheffé, D: Dunnett, HW: Hunter–Worsley, ME: McCann–Edwards.