Nonparametric estimation for probability mass function with Disake: an R package for discrete associated kernel estimators

W.E. Wansouwé (1) , C.C. Kokonendji (2) , D.T. Kolyang (1)

1 The University of Maroua - Department of Computer Science
2 LMB - Laboratoire de Mathématiques de Besançon (UMR 6623)

Kernel smoothing is one of the most widely used nonparametric data smoothing techniques. We introduce a new R package, Disake, for computing discrete associated kernel estimators for probability mass function. When working with a kernel estimator, two choices must be made: the kernel function and the smoothing parameter. The Disake package focuses on discrete associated kernels and also on cross-validation and local Bayesian techniques to select the appropriate bandwidth. Applications on simulated data and real data show that the binomial kernel is appropriate for small or moderate count data while the empirical estimator or the discrete triangular kernel is indicated for large samples.

Mots clés: R package; standard discrete associated kernel; cross-validation

Domaines: Informatique [cs]; Mathématiques [math]

W.E. Wansouwé, C.C. Kokonendji, D.T. Kolyang. Nonparametric estimation for probability mass function with Disake: an R package for discrete associated kernel estimators. Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, 2015, Volume 19 - 2015 - Special issue - CRI'13, pp.1-23. ⟨10.46298/arima.1984⟩. ⟨hal-01300100⟩