Density Estimation Using Inverse and Reciprocal Inverse Guassian Kernels

Olivier Scaillet

No 2001017, LIDAM Discussion Papers IRES from Université catholique de Louvain, Institut de Recherches Economiques et Sociales (IRES)

Abstract: This paper introduces two new nonparametric estimators for probability density functions which have support on the non-negative half-line. These kernel estimators are based on some inverse Gaussian and reciprocal inverse Gaussian probability density functions used as kernels. We show that they share the same properties as those of gamma kernel estimators : they are free of boundary bias, always non-negative, and achieve the optimal rate of convergence for the mean integrated squarred error. Extensions to regression curve estimation and hazard rate estimation under random censoring are briefly discussed. Monte Carlo results concerning finite sample properties are reported for different distributions.

Keywords: Boundary bias; Inverse Gaussian kernel; Reciprocal inverse Gaussian kernel; Gamma kernel; Variable kernel; Density estimation (search for similar items in EconPapers)
JEL-codes: C13 C14 (search for similar items in EconPapers)
Pages: 15
Date: 2001-06-01
New Economics Papers: this item is included in nep-ecm and nep-ets
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://sites.uclouvain.be/econ/DP/IRES/2001-17.pdf (application/pdf)

Related works:
Working Paper: Density Estimation Using Inverse and Reciprocal Inverse Gaussian Kernels (2001)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ctl:louvir:2001017

Access Statistics for this paper

More papers in LIDAM Discussion Papers IRES from Université catholique de Louvain, Institut de Recherches Economiques et Sociales (IRES) Place Montesquieu 3, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Virginie LEBLANC ().