Asymptotic distribution of score statistics for spatial cluster detection with censored data

Daniel Commenges; Benoit Liquet

doi:10.1111/j.1541-0420.2008.01132_1.x

Asymptotic distribution of score statistics for spatial cluster detection with censored data

Daniel Commenges^*, Benoit Liquet

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

Cook, Gold, and Li (2007, Biometrics 63, 540-549) extended the Kulldorff (1997, Communications in Statistics 26, 1481-1496) scan statistic for spatial cluster detection to survival-type observations. Their approach was based on the score statistic and they proposed a permutation distribution for the maximum of score tests. The score statistic makes it possible to apply the scan statistic idea to models including explanatory variables. However, we show that the permutation distribution requires strong assumptions of independence between potential cluster and both censoring and explanatory variables. In contrast, we present an approach using the asymptotic distribution of the maximum of score statistics in a manner not requiring these assumptions.

Original language	English
Pages (from-to)	1287-1292
Number of pages	6
Journal	Biometrics
Volume	64
Issue number	4
DOIs	https://doi.org/10.1111/j.1541-0420.2008.01132_1.x
Publication status	Published - Dec 2008
Externally published	Yes

Keywords

Asymptotic distribution
Cluster detection
Generalized linear model
Permutation test
Score test
Spatial scan statistic
Survival data

Access to Document

10.1111/j.1541-0420.2008.01132_1.x

Cite this

@article{161ea0f6996f466b944de71dc49ed97e,

title = "Asymptotic distribution of score statistics for spatial cluster detection with censored data",

abstract = "Cook, Gold, and Li (2007, Biometrics 63, 540-549) extended the Kulldorff (1997, Communications in Statistics 26, 1481-1496) scan statistic for spatial cluster detection to survival-type observations. Their approach was based on the score statistic and they proposed a permutation distribution for the maximum of score tests. The score statistic makes it possible to apply the scan statistic idea to models including explanatory variables. However, we show that the permutation distribution requires strong assumptions of independence between potential cluster and both censoring and explanatory variables. In contrast, we present an approach using the asymptotic distribution of the maximum of score statistics in a manner not requiring these assumptions.",

keywords = "Asymptotic distribution, Cluster detection, Generalized linear model, Permutation test, Score test, Spatial scan statistic, Survival data",

author = "Daniel Commenges and Benoit Liquet",

year = "2008",

month = dec,

doi = "10.1111/j.1541-0420.2008.01132_1.x",

language = "English",

volume = "64",

pages = "1287--1292",

journal = "Biometrics",

issn = "1541-0420",

publisher = "International Biometric Society",

number = "4",

}

TY - JOUR

T1 - Asymptotic distribution of score statistics for spatial cluster detection with censored data

AU - Commenges, Daniel

AU - Liquet, Benoit

PY - 2008/12

Y1 - 2008/12

N2 - Cook, Gold, and Li (2007, Biometrics 63, 540-549) extended the Kulldorff (1997, Communications in Statistics 26, 1481-1496) scan statistic for spatial cluster detection to survival-type observations. Their approach was based on the score statistic and they proposed a permutation distribution for the maximum of score tests. The score statistic makes it possible to apply the scan statistic idea to models including explanatory variables. However, we show that the permutation distribution requires strong assumptions of independence between potential cluster and both censoring and explanatory variables. In contrast, we present an approach using the asymptotic distribution of the maximum of score statistics in a manner not requiring these assumptions.

AB - Cook, Gold, and Li (2007, Biometrics 63, 540-549) extended the Kulldorff (1997, Communications in Statistics 26, 1481-1496) scan statistic for spatial cluster detection to survival-type observations. Their approach was based on the score statistic and they proposed a permutation distribution for the maximum of score tests. The score statistic makes it possible to apply the scan statistic idea to models including explanatory variables. However, we show that the permutation distribution requires strong assumptions of independence between potential cluster and both censoring and explanatory variables. In contrast, we present an approach using the asymptotic distribution of the maximum of score statistics in a manner not requiring these assumptions.

KW - Asymptotic distribution

KW - Cluster detection

KW - Generalized linear model

KW - Permutation test

KW - Score test

KW - Spatial scan statistic

KW - Survival data

UR - http://www.scopus.com/inward/record.url?scp=56049094355&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2008.01132_1.x

DO - 10.1111/j.1541-0420.2008.01132_1.x

M3 - Article

C2 - 19051394

AN - SCOPUS:56049094355

SN - 1541-0420

VL - 64

SP - 1287

EP - 1292

JO - Biometrics

JF - Biometrics

IS - 4

ER -

Asymptotic distribution of score statistics for spatial cluster detection with censored data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this