Related Experiment Video
Updated: Jun 2, 2026

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
Published on: October 13, 2018
Confidence regions for Bonferroni-based closed tests extended to more general closed tests
Olivier Guilbaud1, Par Karlsson
1AstraZeneca, Sodertalje, Sweden. olivier.guilbaud@astrazeneca.com
Abstract:
Simultaneous confidence regions were recently derived for a large class of Bonferroni-based closed testing procedures (CTPs). This class and a very useful subclass of graphical procedures are described, and it is then shown how the direct approach of Guilbaud (2008) for such CTPs can be extended to cover also CTPs that are not Bonferroni based and that may utilize dependencies not utilized by Bonferroni-based procedures. The simultaneous confidence regions that can be derived through this extension include the known confidence bounds for the step-down version of one-sided Dunnett-type multiple comparisons versus a control in the balanced case. As a simple illustration of how the general results can be applied, similar bounds are derived for the unbalanced case. As a further, more elaborated, illustration, confidence bounds are derived for the Dunnett gatekeeping procedure of Xu et al. (2009) based on a primary and a secondary variable. In this procedure, primary rejections are made through an ordinary one-sided Dunnett procedure, and secondary rejections are restricted to treatment comparisons with primary rejections. It turns out that ordinary Dunnett-type confidence assertions can be made for all primary comparisons without rejections. Interestingly, informative confidence assertions can be made also for secondary comparisons without rejections, but only in case of matching primary rejections. The gatekeeping is thus naturally extended to confidence assertions.
Related Concept Videos
Bonferroni Test
The means of different samples are first paired in all possible combinations.
The null hypothesis of the...
Confidence Intervals
A confidence...
Identifying Statistically Significant Differences: The F-Test
Critical Region, Critical Values and Significance Level
In hypothesis testing, a sample statistic is converted to a test statistic using z, t, or chi-square distribution. A critical region is an area under the curve in probability distributions demarcated by the critical value. When the test statistic falls in this region, it suggests that the null hypothesis must be rejected. As this region contains all those values of the test...
Behrens–Fisher Test
This test is...
Types of Hypothesis Testing
When the null and alternative hypotheses are stated, it is observed that the null hypothesis is a neutral statement against which the alternative hypothesis is tested. The alternative hypothesis is a claim that instead has a certain direction. If the null hypothesis claims that p = 0.5, the alternative hypothesis would be an opposing statement to this and can be put either p > 0.5, p < 0.5, or p ≠ 0.5.

