|
Abstract:
|
Analyzing brain networks has long been a prominent research topic in neuroimaging, yet statistical methods to detect differences between these networks and relate them to phenotypic traits are still sorely needed. Our previous work developed a novel permutation testing framework to detect differences between two groups. Here we advance that work to allow both assessing differences by continuous phenotypes and controlling for confounding variables. To achieve this, we propose an innovative regression framework to relate distances between brain network features to functions of differences in continuous covariates and indicators of difference for categorical variables. We explore several similarity metrics for comparing distances between connection matrices and adapt several methods for estimation and inference within our framework: F-test, F-test with individual level effects, a novel modification of standard Generalized Least Squares, Mixed Model, and Permutation. We assess all approaches for estimation and inference via simulation studies, and illustrate the utility of our framework by analyzing the relationship between fluid intelligence and brain network distances in HCP data.
|
