Figure 7From: A hierarchical Bayesian network approach for linkage disequilibrium modeling and data-dimensionality reduction prior to genome-wide association studiesDirected acyclic graph of the FHLC model learned for unphased genotypes of Daly et al .'s dataset. For node nomenclature, see Figure 6. We recall that in any FHLCM graph, edges are directed from top to bottom. a = 0.2, b = 2, card max = 20, t CAST = 0.95, t MI = quantile MI (0.95), t = 0. 3 (for CFHLC parameter description, see Section Algorithm).Back to article page