Variance reduction in multiparameter likelihood models
Resource
Journal of the American Statistical Association
Journal
Journal of the American Statistical Association
Pages
-
Date Issued
2006-05
Date
2006-05
Author(s)
Peng, Liang
DOI
20060927121122867929
Abstract
Local likelihood modeling is a unified & effective approach to establishing the depen-
dence of a response variable, which can be of various types, on independent variables.
Therefore the methods have become popular in a wide range of applications. There is an increasing interest in employing multiparameter local likelihood models to inves-
tigate trends of sample extremes in environmental statistics. When sample maxima
are modeled by a generalized extreme value distribution, the sample size is small in general & local likelihood estimation exhibits a large variation. In this paper,
variance reduction techniques are employed to improve efficiency of the inference. A simulation study & an application to annual maximum temperatures show that our methods are very effective in finite samples.
Subjects
Bootstrap
extreme value distribution
generalized linear models
local
likelihood
likelihood
local linear MLE
logistic regression
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
likelihood_final.pdf
Size
212.44 KB
Format
Adobe PDF
Checksum
(MD5):a4f6855feec8834f7c771d6220583fef