COMPSTAT 2022: Start Registration
View Submission - COMPSTAT2022
Title: A Bayesian nonparametric estimation of entropy for circular data Authors:  Najmeh Nakhaeirad - University of Pretoria (South Africa) [presenting]
Andriette Bekker - University of Pretoria (South Africa)
Mohammad Arashi - Ferdowsi University of Mashhad (Iran)
Sollie Millard - University of Pretoria (South Africa)
Abstract: Entropy is a widely-used information theoretic measure; however, the major problem in information theoretic analysis of data is the reliable estimation of entropy, especially from small samples. Furthermore, there is a gap in the literature regarding the estimating of entropy for circular data. Circular data comes from several domains with special emphasis on the phases of periodic phenomena and directions such as biology, physics, neuroscience, earth sciences, economics and meteorology. A Bayesian approach is implemented to obtain the nonparametric estimation of Shannon entropy for circular data. Three different estimators are proposed and their performance is compared via a simulation study. We close with the application of Shannon entropy in circular data analysis.