Abstract
dc:description.abstractThis dissertation includes four Chapters. A brief description of each chapter is organized as follows. In Chapter 1, some developments on multiple hypotheses tests are introduced. Some preliminaries about the definition and the assumption are included. In Chapter 2, a Stable Combination Test is proposed to combine $p$-values from multiple hypotheses tests. We show the proposed method controls the family-wise error rate at the target level and maintains asymptotically optimal power even when the elementary p-values from the individual hypotheses are dependent. In Chapter 3, a deeper dig into the additive p-value combination test is performed. A common idea behind some existing combination tests including the Stable Combination Test is extracted and a unified framework is proposed. The tails of the combined test statistics in this framework can be approximated by stable distribution. The tests in this framework are proven to have a well-controlled family-wise error rate and non-trivial power. In Chapter 4, we illustrate the usefulness of the proposed unified framework by capturing the dynamic structure instabilities of Granger causality in a vector autoregression model. The p-value combination tests in the framework are easy to implement, robust to dependence, and have comparable performance to the bootstrap technique.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy in Statistics (PhD)
- Level thesis:degree_level
- Open Access Dissertation
- Discipline thesis:degree_discipline
- Department of Mathematical Sciences
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ling, Xing
- Committee members dc:contributor.committeemember
-
- Iosif Pinelis
- Qiuying Sha
- Kui Zhang
- Chee-Wooi Ten
- Contributors dc:contributor
-
- David Hemmer
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Identifier
- https://digitalcommons.mtu.edu/etdr/1542