HBCGM is the most appropriate method for analyzing phenotypic data obtained from larger numbers of inbred strains, which can have 3 or more distinct phenotypic states. These advantages were illustrated when 3 phenotypic datasets (the response to aromatic hydrocarbons, H2-Eα gene expression, and survival after Candida albicans infection) were analyzed using another computational method, which is used to analyze genetic association studies in mice. The efficient mixed-model association (EMMA) method [12] analyzes the correlation between phenotypic data measured across a set of inbred strains and the alleles at a single SNP, and its ability to correct for population structure and genetic relatedness among the inbred strains has been shown to reduce the false positive rate [13]. Each of these datasets was previously analyzed by HBCGM, and the allelic effect for the gene with the highest correlation was experimentally verified. However, the causative gene for only the aromatic hydrocarbon response could be identified using EMMA [14], because it is a binary response (either present or absent) phenotype. If a binary phenotype is entirely determined by alleles at a single SNP, then
