Fig. 4

Power plots for both the LRT and Wald tests at the fold ratio of 2. Power was calculated at 5 different sample sizes, 5 different mean expression levels, 5 different dispersion values for four tests (LRT under the BNB model, Wald test under the BNB model, LRT under the Poisson-LMM model, LRT under the NB-LMM model) of the fold ratio of 2. The nominal false positive rate α is set at 0.001. The LRT under the BNB model and the LRT under the Poisson-LMM model have equivalent power over different parameter values. But compared to them, the Wald test under the BNB model has higher power and the LRT under the NB-LMM model has lower power at almost all parameter values