Cross-validation method for bivariate measure with certain mixture

4th International Conference on Science & Engineering in Mathematics, Chemistry and Physics 2016

数学;化学;物理学

Sabre, Rachid^1

LE2I UMR6306, CNRS, ENSAM, Univ. Bourgogne Franche-Comté, Agrosup, Département Sciences pour l'Ingénieur et Procédés, 26, Bd Docteur Petitjean, Dijon

21000, France^1

关键词: Bivariate;    Cross validation;    Cross-validation methods;    Discrete measure;    Finite number;    Probability measures;    Rate of convergence;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/710/1/012038/pdf
DOI  :  10.1088/1742-6596/710/1/012038

来源: IOP

【 摘 要 】

We consider a pair of random variables (X, Y) whose probability measure is the sum of an absolutely continuous measure, a discrete measure and a finite number of absolutely continuous measures on several lines. An asymptotically unbiased and consistent estimate of the density of the continuous part is given in [13]. In this work, we focus on the choice of these parameters so that this estimate will be optimal and the rate of convergence will be better, we as well as its rate of convergence. To achieve this we use the cross-validation technics.