Factors Affecting the Power of Haplotype Markers in Association Studies

An important, unresolved question in genome-wide association studies is whether there are predictable differences in power between single nucleotide polymorphism (SNP) and haplotype markers. In this study, we use coalescent simulations to compare power for single-SNP and haplotype markers under a number of different models of demographic history and trait genetic architecture. We find that, across a range of plausible scenarios, the average power of 2- and 3-SNP haplotype markers to detect a quantitative trait locus (QTL) exceeds that of single-SNP markers. The average increase in power is greater when a QTL is due to more than one polymorphism, when the population has experienced a bottleneck, and/or when marker SNPs are ascertained. These results are particularly relevant to applications where populations have experienced bottlenecks and marker density is low.