For large numbers of marker loci in a genomic scan for disease loci, we propose a novel 2-stage
approach for linkage or association analysis. The two stages are (1) selection of a subset of markers
that are ‘important’ for the trait studied, and (2) modelling interactions among markers and between
markers and trait. Here we focus on stage 1 and develop a selection method based on a 2-level nested
bootstrap procedure. The method is applied to single nucleotide polymorphisms (SNPs) data in a
cohort study of heart disease patients. Out of the 89 original SNPs the method selects 11 markers
as being ‘important’. Conventional backward stepwise logistic regression on the 89 SNPs selects 7
markers, which are a subset of the 11 markers chosen by our method.