Figure 9.

Stability diagnostic plot of the identification procedure on multiscale sets of experiments. Multiscale unbiased joint inclusion probability estimates is plotted against a range of experimental scale values $K\in \left[2,200\right]$ for an arbitrary marginal inclusion probability threshold of ${\tilde{p}}_{\text{min}}=0.75$. The plot also displays probability estimate standard errors, the change point ${\widehat{K}}_{\text{min}}$ (${\widehat{K}}_{\text{min}}\in \left[5,15\right]$) and the scatterplot smoothing curves fitted to the data (by LOESS local polynomial regression procedure). These curves are approximately horizontal-flat (i.e. show no trend) for K > Kmin.