Figure 5.

Posterior distribution of ${\tau }_s^2$ assuming ${\beta }_{sg}\sim N(0,{\tau }_s^2)$. The simulated data includes two gene sets, each with 20 genes. For the first gene set, we set the actual values of β_sg to 1, for g = 1, …, 20. For the second gene set, β_sg is set to −1 for half of the genes and to 1 for the remaining genes. The Posterior distribution of ${\tau }_1^2$ and ${\tau }_2^2$ for Set 1 and Set 2 are similar. Therefore, the hyperparameter ${\tau }_s^2$ has captured the location shift in the distribution of β_sg for Set 1, and the scale change for Set 2.