On bandwidth parameter choices for discrete nonparametric kernel estimator

AbstractThis note concentrates on the nonparametric estimation of a probability mass function (p.m.f.) using discrete associated kernels. An expression of the optimal bandwidth minimizing the asymptotic part of the global squared error is given. Some asymptotic expressions of bias and variance of the cross-validation criterion are also presented. At last, the two bandwidth selection procedures are illustrated through some simulations and an application on a real count data set