Premium
Using Data Mining to Address Heterogeneity in the Southampton Data
Author(s) -
Chang Chee Jen,
Fann Cathy S.J.
Publication year - 2001
Publication title -
genetic epidemiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.301
H-Index - 98
eISSN - 1098-2272
pISSN - 0741-0395
DOI - 10.1002/gepi.2001.21.s1.s180
Subject(s) - linkage (software) , nonparametric statistics , quantitative trait locus , statistics , regression analysis , genetic linkage , trait , homogeneous , biology , computational biology , computer science , mathematics , genetics , gene , combinatorics , programming language
When analyzing complex traits such as asthma, heterogeneity needs to be assumed. With this in mind, to identify a more homogeneous group of asthmatic patients, we analyzed the Southampton data using the data mining technique known as the regression tree method and the two most inheritable quantitative phenotypes (LnIgE and RAST) as the target variables. Two‐point and multipoint nonparametric linkage analyses were carried out using one of the subgroups as affected. In addition, we performed quantitative trait loci nonparametric linkage analysis using each phenotype as the outcome. The results from the affected‐sib‐pairs method and quantitative linkage analysis were compared. © 2001 Wiley‐Liss, Inc.