Abstract
AbstractThe simultaneous confidence intervals for all pairwise differences among the proportions are expressed in Hochberg and Tamhane (1987) in k binomial populations. However, the degree of the conservativeness for the simultaneous confidence intervals depends on unknown proportion parameters. Therefore multiple tests based on arcsine transformation for all-pairwise comparison are proposed in Chap. 3. Chapter 3 shows that the degree of the conservativeness for the proposed tests is controlled by the sizes of the samples. For the multiple comparisons with a control, the multiple test procedures based on the Bonferroni inequality are stated in Shiraishi (2009), and Tanaka and Tarumi (1997). By using the arcsine transformation, it can be confirmed that the Dunnett-type multiple tests is superior to the former tests. Lastly a sequentially rejective procedure is discussed as a multi-step procedure.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have