PhD Dissertation Defense
Title: Novel P-value Combination Methods for Signal Detection in Large-Scale Data Analysis.
Abstract: In this dissertation, we first study the distributional properties of, phi-divergence statistics, a family of maximum based goodness-of-fit statistical tests and then we propose, TFisher, a new family of aggregation based test that generalized and optimized the classic Fisher's p-value combination method. The robust versions of these tests are proposed to reduce the sensitivity of statistical power to different signal patterns. We also develop analytical algorithms to efficiently find the p-values of both tests under arbitrary correlation structure so that these optimal methods are not only powerful but also computationally feasible for large-scale data analysis. Both families of tests are successfully applied to detect the joint effect of the genetic association of diseases for whole genome and whole exome sequencing data
Dr. Zheyang Wu (Advisor, WPI)
Dr. Jian Zou (WPI)
Dr. Dmitry Korkin (WPI)
Dr. Jiashun Jin (Carnegie Mellon)
Dr. Jie Cheng (Abbvie Inc.)