A Bottom-up Approach to Testing Hypotheses That Have a Branching Tree Dependence Structure, with False Discovery Rate Control

Abstract

Modern statistical analyses often involve testing large numbers of hypotheses. In many situations, these hypotheses may have an underlying tree structure that not only helps determine the order that tests should be conducted but also imposes a dependency between tests that must be accounted for. Our motivating example comes from testing the association between a trait of interest and groups of microbes that have been organized into operational taxonomic units (OTUs) or amplicon sequence variants (ASVs). Given p-values from association tests for each individual OTU or ASV, we would like to know if we can declare that a certain species, genus, or higher taxonomic grouping can be considered to be associated with the trait. For this problem, a bottom-up testing algorithm that starts at the lowest level of the tree (OTUs or ASVs) and proceeds upward through successively higher taxonomic groupings (species, genus, family etc.) is required. We develop such a bottom-up testing algorithm that controls the error rate of decisions made at higher levels in the tree, conditional on findings at lower levels in the tree. We further show this algorithm controls the false discovery rate based on the global null hypothesis that no taxa are associated with the trait. By simulation, we also show that our approach is better at finding driver taxa, the highest level taxa below which there are dense association signals. We illustrate our approach using data from a study of the microbiome among patients with ulcerative colitis and healthy controls.