🤖 AI Summary
This study addresses circular response data exhibiting directional structure and within-cluster dependence, as commonly encountered in repeated orientation experiments and movement ecology. The authors propose a mixed-effects model within the generalized angular regression framework, defining the mean direction via a two-dimensional consensus vector and incorporating both a von Mises-distributed circular random intercept and a Gaussian scalar random slope. By deriving an analytical marginalization, the marginal likelihood is reduced to a one-dimensional integral, circumventing computationally intensive high-dimensional numerical integration. The work establishes conditions for model identifiability and develops associated asymptotic theory. Simulation studies demonstrate excellent numerical stability and favorable finite-sample performance. Application to sandhopper orientation data confirms the validity and practical utility of the proposed approach for variance component inference.
📝 Abstract
Clustered circular responses arise in repeated orientation experiments, movement ecology, and sensor studies, where both directionality and within-cluster dependence matter. We propose a parsimonious mixed-effects extension of generalized angular regression in which the mean direction is defined by the orientation of a two-dimensional consensus vector. The model combines a von Mises circular random intercept with a pre-specified Gaussian scalar random slope acting on one consensus-vector coefficient. Conditional on the scalar slope, the circular intercept integrates analytically, yielding a one-dimensional marginal likelihood and avoiding the high-dimensional integration required by general random-slope models. We establish high-level design-conditional identifiability conditions, cluster-asymptotic likelihood theory away from the variance boundary, and a practical framework for deterministic quadrature, diagnostics, and model assessment. Simulation studies investigate numerical stability and finite-sample performance. An application to repeated sandhopper orientation data illustrates the proposed methodology and highlights practical considerations for variance-component inference.