Abstract
Network data are increasingly collected along with other variables of interest. Our motivation is drawn from neurophysiology studies measuring brain connectivity networks for a sample of individuals along with their membership to a low or high creative reasoning group. It is of paramount importance to develop statistical methods for testing of global and local changes in the structural interconnections among brain regions across groups. We develop a general Bayesian procedure for inference and testing of group differences in the network structure, which relies on a nonparametric representation for the conditional probability mass function associated with a network-valued random variable. By leveraging a mixture of low-rank factorizations, we allow simple global and local hypothesis testing adjusting for multiplicity. An efficient Gibbs sampler is defined for posterior computation. We provide theoretical results on the flexibility of the model and assess testing performance in simulations. The approach is applied to provide novel insights on the relationships between human brain networks and creativity.
Highlights
There has been an increasing focus on using neuroimaging technologies to better understand the neural pathways underlying human behavior, abilities and neuropsychiatric diseases
Activity measures are available via electroencephalography (EEG) and functional magnetic resonance imaging – among others – and the aim is to produce a spatial map of the locations in the brain across which activity levels display evidence of change with the phenotype (e.g. Genovese et al, 2002; Tansey et al, 2014)
Even if functional connectivity networks are of fundamental interest, the recent developments in diffusion tensor imaging (DTI) technologies (Craddock et al, 2013) have motivated an increasing focus on structural brain network data measuring anatomical connections made by axonal pathways
Summary
There has been an increasing focus on using neuroimaging technologies to better understand the neural pathways underlying human behavior, abilities and neuropsychiatric diseases. Activity measures are available via electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) – among others – and the aim is to produce a spatial map of the locations in the brain across which activity levels display evidence of change with the phenotype Brain connectivity data are available to facilitate this task, with non-invasive imaging technologies providing accurate brain network data at increasing spatial resolution; see Stirling and Elliott (2008), Craddock et al (2013) and Wang et al (2014) for an overview and recent developments. Even if functional connectivity networks are of fundamental interest, the recent developments in diffusion tensor imaging (DTI) technologies (Craddock et al, 2013) have motivated an increasing focus on structural brain network data measuring anatomical connections made by axonal pathways. Refer to Sporns (2013) for a discussion on functional and structural connectivity networks
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have