betaFeedback

WorksMathematics

General Methodology for Asymptotically Balanced Multiple Tests

Abstract

In statistical applications, often more than one hypothesis is of interest and, thus, multiple testing problems occur naturally. To control the family-wise error rate, popular adjustment methods, like the Bonferroni and Holm correction, have been developed. However, these methods do not use the dependence structure of the test statistics. Consequently, they are conservative in most settings. To increase the power of the tests, the joint dependence structure of the test statistics can be incorporated for the construction of critical values, for example, by using resampling schemes as bootstrap procedures to approximate the joint distribution. This has already been applied in several contexts. In this work, we develop a very flexible and general theoretical foundation, which can be used to construct asymptotically balanced multiple tests that control the family-wise error rate in the strong sense. Additionally, we prove in the general setting that consistent resampling schemes satisfy the needed conditions.

Paper details

vlnc:W_6njbgav7
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC-BY-NC-ND-4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…