CaltechAUTHORS
  A Caltech Library Service

Refined normal approximations for the central and noncentral chi-square distributions and some applications

Ouimet, Frédéric (2022) Refined normal approximations for the central and noncentral chi-square distributions and some applications. Statistics, 56 (4). pp. 935-956. ISSN 0233-1888. doi:10.1080/02331888.2022.2084544. https://resolver.caltech.edu/CaltechAUTHORS:20220913-19298800

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20220913-19298800

Abstract

In this paper, we prove a local limit theorem for the chi-square distribution with r>0 degrees of freedom and noncentrality parameter λ≥0. We use it to develop refined normal approximations for the survival function. Our maximal errors go down to an order of r−2, which is significantly smaller than the maximal error bounds of order r−1/2 recently found by Horgan and Murphy [On the convergence of the chi square and noncentral chi square distributions to the normal distribution. IEEE Commun Lett. 2013;17(12):2233–2236. DOI:10.1109/LCOMM.2013.111113.131879] and Seri [A tight bound on the distance between a noncentral chi square and a normal distribution. IEEE Commun Lett. 2015;19(11):1877–1880. DOI:10.1109/LCOMM.2015.2461681]. Our results allow us to drastically reduce the number of observations required to obtain negligible errors in the energy detection problem, from 250, as recommended in the seminal work of Urkowitz [Energy detection of unknown deterministic signals. Proc IEEE. 1967;55(4):523–531. DOI:10.1109/PROC.1967.5573], to only 8 here with our new approximations. We also obtain an upper bound on several probability metrics between the central and noncentral chi-square distributions and the standard normal distribution, and we obtain an approximation for the median that improves the lower bound previously obtained by Robert [On some accurate bounds for the quantiles of a noncentral chi squared distribution. Stat Probab Lett. 1990;10(2):101–106. Available from: https://www.ams.org/mathscinet-getitem?mr=MR1072495].


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1080/02331888.2022.2084544DOIArticle
ORCID:
AuthorORCID
Ouimet, Frédéric0000-0001-7933-5265
Additional Information:We thank Robert Ferydouni (University of California – Santa Cruz) for collecting some of the references in Section 2 and helping us use the latex2exp package in R. F. Ouimet is supported by postdoctoral fellowships from the Natural Sciences and Engineering Research Council of Canada and the Fond québécois de la recherche – Nature et technologies (B3X supplement and B3XR).
Funders:
Funding AgencyGrant Number
Natural Sciences and Engineering Research Council of Canada (NSERC)UNSPECIFIED
Fonds de recherche du Québec - Nature et technologies (FRQNT)B3X
Fonds de recherche du Québec – Nature et technologies (FRQNT)B3XR
Issue or Number:4
DOI:10.1080/02331888.2022.2084544
Record Number:CaltechAUTHORS:20220913-19298800
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20220913-19298800
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:116905
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:03 Oct 2022 22:24
Last Modified:03 Oct 2022 22:24

Repository Staff Only: item control page