Confidence regions for bivariate probability density functions using polygonal areas

Authors : Orhan KESEMEN, Eda ÖZKUL, Ülkü ÜNSAL

Pages : 276-306

Doi:10.31801/cfsuasmas.542499

View : 9 | Download : 6

Publication Date : 2020-06-30

Article Type : Research Paper

Abstract :In this study, a polygonal approach is suggested to generalize the notion of the condence region of the univariate probability density function for the bivariate probability density function. The equal density approach is used to demonstrate that condence regions can be polygonal shapes. The bisection method is the preferred method in nding the equal density value that reveals the desired condence coecient. Condence regions estimate not only bivariate unimodal probability functions but also bivariate multimodal probability functions. An approach is enhanced to estimate these condence regions for probability density functions which are dened as rectangular, polygonal and innite expanse areas.
Keywords : bivariate probability density functions, Bivariate confidence region, multimodal confidence region, polygonal confidence region