Home > Research > Publications & Outputs > Maximum kernel likelihood estimation

Research

Associated organisational unit

Electronic data

View graph of relations

Maximum kernel likelihood estimation

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Maximum kernel likelihood estimation. / Jaki, Thomas; West, R. Webster.
In: Journal of Computational and Graphical Statistics, Vol. 17, No. 4, 2008, p. 976-993.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Jaki, T & West, RW 2008, 'Maximum kernel likelihood estimation', Journal of Computational and Graphical Statistics, vol. 17, no. 4, pp. 976-993.

APA

Jaki, T., & West, R. W. (2008). Maximum kernel likelihood estimation. Journal of Computational and Graphical Statistics, 17(4), 976-993.

Vancouver

Jaki T, West RW. Maximum kernel likelihood estimation. Journal of Computational and Graphical Statistics. 2008;17(4):976-993.

Author

Jaki, Thomas ; West, R. Webster. / Maximum kernel likelihood estimation. In: Journal of Computational and Graphical Statistics. 2008 ; Vol. 17, No. 4. pp. 976-993.

Bibtex

@article{fc5d341e3e6c4848844ca71a5061f761,
title = "Maximum kernel likelihood estimation",
abstract = "We introduce an estimator for the population mean based on maximizing likelihoods formed by parameterizing a kernel density estimate. Due to these origins, we have dubbed the estimator the maximum kernel likelihood estimate (mkle). A speedy computational method to compute the mkle based on binning is implemented in a simulation study which shows that the mkle at an optimal bandwidth is decidedly superior in terms of efficiency to the sample mean and other measures of location for heavy tailed symmetric distributions. An empirical rule and a computational method to estimate this optimal bandwidth are developed and used to construct bootstrap confidence intervals for the population mean. We show that the intervals have approximately nominal coverage and have significantly smaller average width than the standard t and z intervals. Lastly, we develop some mathematical properties for a very close approximation to the mkle called the kernel mean. In particular, we demonstrate that the kernel mean is indeed unbiased for the population mean for symmetric distributions.",
author = "Thomas Jaki and West, {R. Webster}",
year = "2008",
language = "English",
volume = "17",
pages = "976--993",
journal = "Journal of Computational and Graphical Statistics",
issn = "1061-8600",
publisher = "American Statistical Association",
number = "4",

}

RIS

TY - JOUR

T1 - Maximum kernel likelihood estimation

AU - Jaki, Thomas

AU - West, R. Webster

PY - 2008

Y1 - 2008

N2 - We introduce an estimator for the population mean based on maximizing likelihoods formed by parameterizing a kernel density estimate. Due to these origins, we have dubbed the estimator the maximum kernel likelihood estimate (mkle). A speedy computational method to compute the mkle based on binning is implemented in a simulation study which shows that the mkle at an optimal bandwidth is decidedly superior in terms of efficiency to the sample mean and other measures of location for heavy tailed symmetric distributions. An empirical rule and a computational method to estimate this optimal bandwidth are developed and used to construct bootstrap confidence intervals for the population mean. We show that the intervals have approximately nominal coverage and have significantly smaller average width than the standard t and z intervals. Lastly, we develop some mathematical properties for a very close approximation to the mkle called the kernel mean. In particular, we demonstrate that the kernel mean is indeed unbiased for the population mean for symmetric distributions.

AB - We introduce an estimator for the population mean based on maximizing likelihoods formed by parameterizing a kernel density estimate. Due to these origins, we have dubbed the estimator the maximum kernel likelihood estimate (mkle). A speedy computational method to compute the mkle based on binning is implemented in a simulation study which shows that the mkle at an optimal bandwidth is decidedly superior in terms of efficiency to the sample mean and other measures of location for heavy tailed symmetric distributions. An empirical rule and a computational method to estimate this optimal bandwidth are developed and used to construct bootstrap confidence intervals for the population mean. We show that the intervals have approximately nominal coverage and have significantly smaller average width than the standard t and z intervals. Lastly, we develop some mathematical properties for a very close approximation to the mkle called the kernel mean. In particular, we demonstrate that the kernel mean is indeed unbiased for the population mean for symmetric distributions.

M3 - Journal article

VL - 17

SP - 976

EP - 993

JO - Journal of Computational and Graphical Statistics

JF - Journal of Computational and Graphical Statistics

SN - 1061-8600

IS - 4

ER -