Examples of simulated ECDFs (in black) for different valid numbers of transits N and their median (in red). The ordinate gives the probability to reject the null-hypothesis of white-noise as a function of the height of the peak (Θ_F statistic of Eq. (9)). Panels a, b and c correspond to N = 10, 17 and 30 respectively. The number of simulated ECDFs in each panel mirrors the proportion of valid transits in the actual data. The sampling time statistically tends to be similar for large N values, leading to a decrease in ECDF dispersion when N increases.