|
Abstract:
The recent literature contains theorems improving on both the Standard Bonferroni inequality and the Sidak/Slepian inequalities. The application of these improved theorems to upper bounds for non-coverage of simultaneous confidence intervals on multivariate normal variables is explored. The improved Bonferroni upper bounds will always apply, while improved Sidak/ Slepian bounds only apply to special cases. The improved Sidak/Slepian upper bound, if it applies, is always superior to the equivalent improved Bonferroni bound. This improvement, however, is not great when both methods are used to determine upper bounds for Type I error in the range of .01 to .10. It is shown that improved Sidak/Slepian bounds will apply to Normal Markov Processes, a commonly occurring and easily identifiable class of multivariate normal variables. (JHD)
| Limitations: |
 APPROVED FOR PUBLIC RELEASE |
| Description: |
Technical rept. |
| Pages: |
20 |
| Report Date: |
23 FEB 89 |
| Contract Number: |
N00014-86-K-0156 |
| Report Number: |
A996602 |
|
|
|
|
|
Keywords relating to this report:
Email This Abstract
