Unimodality in Circular Data: A Bayes Test
Sanjib Basu, S. Rao Jammalamadaka · 2019
Circular data which represent directions in two dimensions, may be measured as angles. Unimodality, which is often assumed, is a crucial issue since modeling and further inference depend on it. Just as on the real line, descriptive as well as inference tools are different for unimodal data as opposed to multi-modal data. We propose a Bayesian test for unimodality of circular data using mixtures of von-Mises distribution as the alternative. The proposed test is performed and evaluated using Markov Chain Monte-Carlo methodology.