We consider several methods of constructing confidence intervals for the noncentrality parameter λ2 of the noncentral chi-squared distribution, based on a single observation, y2. The problem is not straightforward because the parameter space has a finite end-point at λ2 = 0: λ2 is not allowed to be negative, yet λ2 = 0 is feasible. Practical applications include asymptotic interval estimates for multiple correlation coefficients. Bayesian intervals are also discussed. Our overall recommendation is for the use of a ‘symmetric range’ confidence interval.
Описание
Confidence intervals for the noncentral chi-squared distribution
%0 Journal Article
%1 Kent1995147
%A Kent, John T.
%A Hainsworth, Timothy J.
%D 1995
%J Journal of Statistical Planning and Inference
%K chisquare confidence-interval distributions noncentral statistics
%N 2
%P 147 - 159
%R http://dx.doi.org/10.1016/0378-3758(94)00104-4
%T Confidence intervals for the noncentral chi-squared distribution
%U http://www.sciencedirect.com/science/article/pii/0378375894001044
%V 46
%X We consider several methods of constructing confidence intervals for the noncentrality parameter λ2 of the noncentral chi-squared distribution, based on a single observation, y2. The problem is not straightforward because the parameter space has a finite end-point at λ2 = 0: λ2 is not allowed to be negative, yet λ2 = 0 is feasible. Practical applications include asymptotic interval estimates for multiple correlation coefficients. Bayesian intervals are also discussed. Our overall recommendation is for the use of a ‘symmetric range’ confidence interval.
@article{Kent1995147,
abstract = {We consider several methods of constructing confidence intervals for the noncentrality parameter λ2 of the noncentral chi-squared distribution, based on a single observation, y2. The problem is not straightforward because the parameter space has a finite end-point at λ2 = 0: λ2 is not allowed to be negative, yet λ2 = 0 is feasible. Practical applications include asymptotic interval estimates for multiple correlation coefficients. Bayesian intervals are also discussed. Our overall recommendation is for the use of a ‘symmetric range’ confidence interval. },
added-at = {2015-05-26T21:53:53.000+0200},
author = {Kent, John T. and Hainsworth, Timothy J.},
biburl = {https://www.bibsonomy.org/bibtex/2bc60450c6d1163a2ec9f250abc878f18/shabbychef},
description = {Confidence intervals for the noncentral chi-squared distribution},
doi = {http://dx.doi.org/10.1016/0378-3758(94)00104-4},
interhash = {34d141f10419cf88421f55135abc7af5},
intrahash = {bc60450c6d1163a2ec9f250abc878f18},
issn = {0378-3758},
journal = {Journal of Statistical Planning and Inference },
keywords = {chisquare confidence-interval distributions noncentral statistics},
number = 2,
pages = {147 - 159},
timestamp = {2015-05-26T21:53:53.000+0200},
title = {Confidence intervals for the noncentral chi-squared distribution },
url = {http://www.sciencedirect.com/science/article/pii/0378375894001044},
volume = 46,
year = 1995
}