Maximizing leave-one-out likelihood for the location parameter of unbounded densities
(2015) In Annals of the Institute of Statistical Mathematics 67(1). p.19-38- Abstract
- We propose simple estimation of the location parameter for a density that is unbounded at the mode. The estimator maximizes a modified likelihood in which the singular term in the full likelihood is left out, whenever the parameter value approaches a neighborhood of the singularity location. The consistency and super-efficiency of this maximum leave-one-out likelihood estimator is shown through a direct argument. The importance for estimation within parametric families is discussed and illustrated by an example involving the gamma mixture of normal distributions.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/5075977
- author
- Podgorski, Krzysztof LU and Wallin, Jonas LU
- organization
- publishing date
- 2015
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Unbounded likelihood, Location parameter, Super-efficiency, Generalized, asymmetric Laplace distribution
- in
- Annals of the Institute of Statistical Mathematics
- volume
- 67
- issue
- 1
- pages
- 19 - 38
- publisher
- Springer
- external identifiers
-
- wos:000347692100002
- scopus:84921068789
- ISSN
- 0020-3157
- DOI
- 10.1007/s10463-013-0437-6
- language
- English
- LU publication?
- yes
- id
- 56487e86-c52f-49d2-a20b-a917357bd6ba (old id 5075977)
- date added to LUP
- 2016-04-01 12:51:44
- date last changed
- 2022-01-27 08:01:33
@article{56487e86-c52f-49d2-a20b-a917357bd6ba,
abstract = {{We propose simple estimation of the location parameter for a density that is unbounded at the mode. The estimator maximizes a modified likelihood in which the singular term in the full likelihood is left out, whenever the parameter value approaches a neighborhood of the singularity location. The consistency and super-efficiency of this maximum leave-one-out likelihood estimator is shown through a direct argument. The importance for estimation within parametric families is discussed and illustrated by an example involving the gamma mixture of normal distributions.}},
author = {{Podgorski, Krzysztof and Wallin, Jonas}},
issn = {{0020-3157}},
keywords = {{Unbounded likelihood; Location parameter; Super-efficiency; Generalized; asymmetric Laplace distribution}},
language = {{eng}},
number = {{1}},
pages = {{19--38}},
publisher = {{Springer}},
series = {{Annals of the Institute of Statistical Mathematics}},
title = {{Maximizing leave-one-out likelihood for the location parameter of unbounded densities}},
url = {{http://dx.doi.org/10.1007/s10463-013-0437-6}},
doi = {{10.1007/s10463-013-0437-6}},
volume = {{67}},
year = {{2015}},
}