Semi‐Parametric Least‐Area Linear‐Circular Regression Through Möbius Transformation

• DOI: 10.1002/sam.70012
• Publication Date: 2025-01-24T06:19:16Z
• Authors: Surojit Biswas; Buddhananda Banerjee

ABSTRACT This paper introduces a novel regression model designed for angular response variables with linear predictors, utilizing generalized Möbius transformation to define the curve. By mapping real axis circle, effectively captures relationship between and components. A key innovation is introduction of an area‐based loss function, inspired by geometry curved torus, efficient parameter estimation. The semi‐parametric nature eliminates need specific distributional assumptions about error, enhancing its versatility. Extensive simulation studies, incorporating von Mises wrapped Cauchy distributions, highlight robustness framework. model's practical utility demonstrated through real‐world data analysis Bitcoin Ethereum, showcasing ability derive meaningful insights from complex structures.