Figure 2.

(a) Empirical reverse cumulative distribution functions (cdfs) of the estimated optimal surrogate ${\psi }_n^{\#}\left(W_i,A_i=a,S_i\right)$ for the CYD14 trial by vaccine/placebo assignment A = a ∈ {0, 1} and dengue outcome case/control status Y = y ∊, {0, 1}. (b) Empirical reverse cdfs of ${\psi }_n^{\#}\left(W_i,A_i=a,S_i^{*}\right)$ for CYD15 participants by vaccine/placebo assignment A* = a ∈ {0, 1} and dengue outcome case/control status Y* = y ∈ {0, 1}, where ${\psi }_n^{\#}(\cdot )$ was estimated from the CYD14 trial data. The results show that the surrogate better classifies dengue outcomes of participants in the original trial than in the new trial (not surprisingly).