Nonparametric series density estimation and testing

This paper .rst establishes consistency of the exponential series density estimator when nuisance parameters are estimated as a preliminary step. Convergence in relative entropy of the density estimator is preserved, which in turn implies that the quantiles of the population density can be consisten...

Full description

Bibliographic Details
Main Author: Marsh, Patrick
Format: Article
Published: Springer 2018
Subjects:
Online Access:https://eprints.nottingham.ac.uk/52926/
_version_ 1848798841647661056
author Marsh, Patrick
author_facet Marsh, Patrick
author_sort Marsh, Patrick
building Nottingham Research Data Repository
collection Online Access
description This paper .rst establishes consistency of the exponential series density estimator when nuisance parameters are estimated as a preliminary step. Convergence in relative entropy of the density estimator is preserved, which in turn implies that the quantiles of the population density can be consistently estimated. The density estimator can then be employed to provide a test for the specification of fitted density functions. Commonly, this testing problem has utilized statistics based upon the empirical distribution function (edf), such as the Kolmogorov-Smirnov or Cramér von-Mises, type. However, the tests of this paper are shown to be asymptotically pivotal having limiting standard normal distribution, unlike those based on the edf. For comparative purposes with those tests, the numerical properties of both the density estimator and test are explored in a series of experiments. Some general superiority over commonly used edf based tests is evident, whether standard or bootstrap critical values are used.
first_indexed 2025-11-14T20:26:11Z
format Article
id nottingham-52926
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T20:26:11Z
publishDate 2018
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling nottingham-529262020-05-04T19:45:38Z https://eprints.nottingham.ac.uk/52926/ Nonparametric series density estimation and testing Marsh, Patrick This paper .rst establishes consistency of the exponential series density estimator when nuisance parameters are estimated as a preliminary step. Convergence in relative entropy of the density estimator is preserved, which in turn implies that the quantiles of the population density can be consistently estimated. The density estimator can then be employed to provide a test for the specification of fitted density functions. Commonly, this testing problem has utilized statistics based upon the empirical distribution function (edf), such as the Kolmogorov-Smirnov or Cramér von-Mises, type. However, the tests of this paper are shown to be asymptotically pivotal having limiting standard normal distribution, unlike those based on the edf. For comparative purposes with those tests, the numerical properties of both the density estimator and test are explored in a series of experiments. Some general superiority over commonly used edf based tests is evident, whether standard or bootstrap critical values are used. Springer 2018-07-08 Article PeerReviewed Marsh, Patrick (2018) Nonparametric series density estimation and testing. Statistical Methods and Applications . ISSN 1618-2510 (In Press) Goodness-of-fit Nonparametric likelihood ratio Nuisance Parameters and Series Density Estimator
spellingShingle Goodness-of-fit
Nonparametric likelihood ratio
Nuisance Parameters and Series Density Estimator
Marsh, Patrick
Nonparametric series density estimation and testing
title Nonparametric series density estimation and testing
title_full Nonparametric series density estimation and testing
title_fullStr Nonparametric series density estimation and testing
title_full_unstemmed Nonparametric series density estimation and testing
title_short Nonparametric series density estimation and testing
title_sort nonparametric series density estimation and testing
topic Goodness-of-fit
Nonparametric likelihood ratio
Nuisance Parameters and Series Density Estimator
url https://eprints.nottingham.ac.uk/52926/