🤖 AI Summary
This paper addresses the challenge of covariate modeling for spatial directional data—such as wind direction and white-matter fiber orientation—by proposing the first covariate-driven von Mises–Fisher (vMF) spatial regression model. Methodologically: (1) it introduces an interpretable link function based on Cartesian–spherical coordinate transformation to explicitly model covariate effects on the spherical mean direction; (2) it incorporates a spherical spatial autoregressive structure to capture directional dependence on the unit sphere; and (3) it establishes a Bayesian inference framework that balances computational efficiency with statistical robustness. Applied to the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, the model uncovers statistically significant spatial associations between cognitive impairment and white-matter fiber orientation. Simulation studies confirm high parameter estimation accuracy, strong robustness to model misspecification, and superior interpretability.
📝 Abstract
Spatially varying directional data are routinely observed in several modern applications such as meteorology, biology, geophysics, and engineering, etc. However, only a few approaches are available for covariate-dependent statistical analysis for such data. To address this gap, we propose a novel generalized linear model to analyze such that using a von Mises Fisher (vMF) distributed error structure. Using a novel link function that relies on the transformation between Cartesian and spherical coordinates, we regress the vMF-distributed directional data on the external covariates. This regression model enables us to quantify the impact of external factors on the observed directional data. Furthermore, we impose the spatial dependence using an autoregressive model, appropriately accounting for the directional dependence in the outcome. This novel specification renders computational efficiency and flexibility. In addition, a comprehensive Bayesian inferential toolbox is thoroughly developed and applied to our analysis. Subsequently, employing our regression model to the Alzheimer's Disease Neuroimaging Initiative (ADNI) data, we gain new insights into the relationship between cognitive impairment and the orientations of brain fibers along with examining empirical efficacy through simulation experiments.
