Bernstein Polynomial Model for Grouped Continuous Data
Author:
Preprint
Abstract
Grouped data are commonly encountered in applications. The Bernstein polynomial model is proposed as an approximate model in this paper for estimating a univariate density function based on grouped data. The coefficients of the Bernstein polynomial, as the mixture proportions of beta distributions, can be estimated using an EM algorithm. The optimal degree of the Bernstein polynomial can be determined using a change-point estimation method. The rate of convergence of the proposed density estimate to the true density is proved to be almost parametric by an acceptance-rejection arguments used in Monte Carlo method. The proposed method is compared with some existing methods in a simulation study and is applied to a real dataset.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Efficient and robust density estimation using Bernstein type polynomialsJournal of Nonparametric Statistics, 2016
- Kernel density estimation on grouped data: the case of poverty assessmentThe Journal of Economic Inequality, 2012
- Robust and efficient estimation under data groupingBiometrika, 2006
- A model for failure of a chicken embryo to survive incubationPoultry Science, 2003
- NONPARAMETRIC ESTIMATION WITH AGGREGATED DATAEconometric Theory, 2002
- Kernel density estimation with binned dataCommunications in Statistics - Theory and Methods, 1985
- Kernel-based density estimation using censored, truncated or grouped dataCommunications in Statistics - Theory and Methods, 1983
- Polynomials with positive coefficients: Uniqueness of best approximationJournal of Approximation Theory, 1977
- The degree of approximation by polynomials with positive coefficientsMathematische Annalen, 1963
- Grouping corrections and maximum likelihood equationsMathematical Proceedings of the Cambridge Philosophical Society, 1950