Skip to main content
Figure 2 | BMC Proceedings

Figure 2

From: A dual-clustering framework for association screening with whole genome sequencing data and longitudinal traits

Figure 2

Average ROC curves across simulation replicates for 3 methods. Shown are results by 10 clusters using inverse-probability weighting. Areas under the curve (AUCs) by different methods are compared using paired Wilcoxon signed rank tests based on the 200 replicates, with the resulting p values shown in the table below. fpr, ie, false positive rate, is the ratio of the number of claimed causal genes and the number of true noncausal genes; tpr, ie, true positive rate, is the ratio of the number of claimed causal genes and the number of true causal genes.

Back to article page