A genetic algorithm for irregularly shaped spatial scan statistics

被引：66

作者：

Duczmal, Luiz

Cancado, Andre L. F.

Takahashi, Ricardo H. C.

Bessegato, Lupercio E.

机构：

[1] Univ Fed Minas Gerais, Dept Stat, BR-31270901 Belo Horizonte, MG, Brazil

[2] Univ Fed Minas Gerais, Dept Elect Engn, Belo Horizonte, MG, Brazil

[3] Univ Fed Minas Gerais, Dept Mat, Belo Horizonte, MG, Brazil

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 2007年 / 52卷 / 01期

关键词：

power evaluation; genetic algorithm; non-compactness penalty; spatial scan statistic;

D O I：

10.1016/j.csda.2007.01.016

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

A new approach is presented for the detection and inference of irregularly shaped spatial clusters, using a genetic algorithm. Given a map divided into regions with corresponding populations at risk and cases, the graph-related operations are minimized by means of a fast offspring generation and efficient evaluation of Kuldorff's spatial scan statistic. A penalty function based on the geometric non-compactness concept is employed to avoid excessive irregularity of cluster geometric shape. The algorithm is an order of magnitude faster and exhibits less variance compared to the simulated annealing scan, and is more flexible than the elliptic scan. It has about the same power of detection as the simulated annealing scan for mildly irregular clusters and is superior for the very irregular ones. An application to breast cancer clusters in Brazil is discussed. (c) 2007 Elsevier B.V. All rights reserved.

引用

页码：43 / 52

页数：10

共 23 条

[1]

ANDRADE LSS, 2004, CAD SAUDE PUBLICA, V20, P411

[2]

[Anonymous], 1999, DIS MAPPING RISK ASS

[3] Fast detection of arbitrarily shaped disease clusters [J].