Circular-Linear Regression: Modeling Directional Outcomes with Bayesian Implementation

Chinonso Michael Eze; Charity Uchenna Onwuamaeze

doi:10.56201/ijasmt.vol.12.no1.2026pg49.59

📄 Download Paper

Circular-Linear Regression: Modeling Directional Outcomes with Bayesian Implementation

Chinonso Michael Eze, Charity Uchenna Onwuamaeze

Abstract

Modeling directional or angular outcomes presents unique statistical challenges due to the periodic nature of circular data. Traditional linear regression techniques are inadequate for such data structures, necessitating the use of circular-linear regression models. This study investigates the relationship between a linear predictor and a circular response variable using a model with an exponential link function. Both the classical approach (the Maximum likelihood estimation method and circular least squares method) and the Bayesian framework are employed to estimate the model parameters, allowing the incorporation of prior knowledge and a probabilistic interpretation of the estimates. Posterior distributions are obtained through Markov Chain Monte Carlo methods, and high-density intervals are used to assess convergence and credibility. The results demonstrate that the model effectively captures the non-linear and periodic relationship between wind direction and speed, and the Bayesian approach provides a robust framework for inference under uncertainty. This work highlights the importance and flexibility of Bayesian circular-linear regression in applications involving directional data, with potential implications across disciplines, such as meteorology, biology, neuroscience, and environmental science.

Keywords

Circular data; exponential link function; circular-linear regression; Bayesian framework; wind data.

References

Arnold B. C and SenGupta, A. (2006). Recent advances in the analysis of directional data in ecological and environmental sciences. Environmental and ecological statistics, 13(3), 253 – 256. Fernández?Durán, J. J. (2007). Models for circular–linear and circular–circular data constructed from circular distributions based on nonnegative trigonometric sums. Biometrics, 63(2), 579-585. Fisher, N. I, and Lee, A. J. (1992). Regression Models for an Angular Response. Biometrics 48, 665-677. Gill, J, and Hangartner, D. (2009). Bayesian circular-linear regression. Seminar on Bayesian Inference in Econometrics and Statistics Gould, A. L. (1969). A regression technique for angular variates. Biometrics 25, 683-700. Heyes, S. B., Zokaei, N., and Husain, M. (2016). Longitudinal development of visual working memory precision in childhood and early adolescence. Cogn. Dev. 39, 36–44. doi: 10.1016/j.cogdev.2016.03.004. Ibrahim, A. I and Xu, G. (2024). Bayesian approach to circular-linear regression with application. AIP Conf. Proc. 3189, 100010. https://doi.org/10.1063/5.0224434 Johnson, R. A. and Wehrly, T. E. (1978). Some angular-linear distribution models. Journal of the American Statistical Association 73, 602-606. Kim S and SenGupta A. (2015). Inverse circular–linear/linear–circular regression Communications in Statistics-Theory and Methods 44(22), 4772-4782 Kirschner, S., and Tomasello, M. (2009). Joint drumming: social context facilitates synchronization in preschool children. J. Exp. Child Psychol. 102, 299–314. doi: 10.1016/j.jecp.2008.07.005. Mardia, K. V. (1976). Linear-Circular Correlation Coefficients and Rhythmometry. Biometrics 63(2), 403-405. Mardia, K. V. and Sutton, T. W. (1978). A model with cylindrical variables with applications. Journal of the Royal Statistical Society, Series B 40, 229-233. McVinish, R. and Mengersen, K. (2008). Semiparametric Bayesian circular statistics. Computational Statistics & Data Analysis, Vol. 52 (10), 4722-4730. Mohammad, H. H., Satari, S. Z. and Yusoff, W. S. (2021). Review on circular-linear regression models. J. Phys.: Conf. Ser. 1988 012108. Mutwiri, R. M. (2016). Application of multiple circular–linear regression models to animal movement data with covariates (Doctoral dissertation). University of KwaZulu-Natal, Durban, South Africa. Retrieved from https://repository.seku.ac.ke/handle/123456789/6351 SenGupta, A. and Ugwuowo, F. I. (2006). Asymmetric circular-linear multivariate regression models with applications to environmental data. Environ. Ecol. Stat., 13, 299–309. DOI10.1007/s10651-005-0013-1 Warren, W. H., Rothman, D. B., Schnapp, B. H., and Ericson, J. D. (2017). Wormholes in virtual space: From cognitive maps to cognitive graphs. Cognition 166, 152–163. doi: 10.1016/j.cognition.2017. 05.020

Circular-Linear Regression: Modeling Directional Outcomes with Bayesian Implementation

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF APPLIED SCIENCES AND MATHEMATICAL THEORY