CFE 2020: Start Registration
View Submission - CMStatistics
Title: Rarefaction-based extensions of the LDM and PERMANOVA for testing presence-absence associations in the microbiome Authors:  Yijuan Hu - Emory University (United States) [presenting]
Andrea Lane - Emory University (United States)
Glen Satten - Emory University (United States)
Abstract: Many methods for testing association between the microbiome and covariates of interest assume that these associations are driven by changes in the relative abundance of taxa. However, these associations may also result from changes in which taxa are present and which are absent. Analyses of such presence-absence associations face a unique challenge: confounding by library size. It is known that rarefaction controls this bias, but at the potential cost of information loss as well as the introduction of a stochastic component in the analysis. Currently, there is a need for robust and efficient methods for testing presence-absence associations in the presence of such confounding, both at the community level and at the individual-taxon level, that avoid the drawbacks of rarefaction. Here we present extensions of the LDM and PERMANOVA for testing presence-absence associations. The extended LDM and PERMANOVA are both non-stochastic approaches that repeatedly apply the LDM and PERMANOVA to all rarefied taxa count tables, averages the residual sum-of-squares (RSS) terms over the rarefaction replicates, and then forms an F-statistic based on these average RSS terms. Our simulations indicate that our proposed methods are robust to any systematic differences in library size and have better power than alternative approaches. We illustrate our method using an analysis of data on inflammatory bowel disease (IBD) in which cases have systematically smaller library sizes than controls.