Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10327503 | Computational Statistics & Data Analysis | 2013 | 8 Pages |
Abstract
The construction of a set of simultaneous confidence intervals for any finite number of contrasts of p generally correlated normal means is considered. It is shown that the simultaneous confidence level can be expressed as a (pâ2)-dimensional integral for a general pâ¥3. This expression allows one to compute quickly and accurately, by using numerical quadrature, the required critical constants and multiplicity adjusted p-values for at least p=3, 4 and 5, involving only one-, two- and three-dimensional integrals, respectively. Real data examples from a drug stability study and a dose response study are used to illustrate the method.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computational Theory and Mathematics
Authors
W. Liu, P. Ah-Kine, F. Bretz, A.J. Hayter,