An adaptive correlation ratio method using the cumulative sum of the reordered output

We consider correlation ratios as estimators for first order sensitivity indices from given data. The computation is simplified by the introduction of the cumulative sum of the normalised reordered output. Ideas for the estimation using interpolation are also discussed.

► Visualise sensitivity properties via cumulative sums of normalised reordered output (CUSUNORO) curves.
► Estimation of first order effects via correlation ratios (CR).
► Adaptive partition layout for (CR) using the CUSUNORO curve.
► Estimation of first order effects using interpolation of the CUSUNORO curve.
► Comparison of methods.