Multiple combined gamma kernel estimations for nonnegative data with Bayesian adaptive bandwidths
From MaRDI portal
Publication:6505484
DOI10.1007/S00180-023-01327-7arXiv2202.09314MaRDI QIDQ6505484FDOQ6505484
Authors: Sobom M. Somé, Célestin C. Kokonendji, Smail Adjabi, N. A. Khan, Said Beddek 
Abstract: A modified gamma kernel should not be automatically preferred to the standard gamma kernel, especially for univariate convex densities with a pole at the origin. In the multivariate case, multiple combined gamma kernels, defined as a product of univariate standard and modified ones, are here introduced for nonparametric and semiparametric smoothing of unknown orthant densities with support . Asymptotical properties of these multivariate associated kernel estimators are established. Bayesian estimation of adaptive bandwidth vectors using multiple pure combined gamma smoothers, and in semiparametric setup, are exactly derived under the usual quadratic function. The simulation results and four illustrations on real datasets reveal very interesting advantages of the proposed combined approach for nonparametric smoothing, compare to both pure standard and pure modified gamma kernel versions, and under integrated squared error and average log-likelihood criteria.
Asymptotic properties of nonparametric inference (62G20) Estimation in multivariate analysis (62H12) Nonparametric inference (62G99)
This page was built for publication: Multiple combined gamma kernel estimations for nonnegative data with Bayesian adaptive bandwidths
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6505484)
