Fig. 2From: Should analyses of large, national palliative care data sets with patient reported outcomes (PROs) be restricted to services with high patient participation? A register-based studyGraph showing how the study hypothesis is tested in the study according to four criteria. *S/Ps = the nine symptoms/problems and overall QOL. **A ‘case’ for each pairwise comparison of S/P mean scores between the ≥60.0% response rate group and a lower response rate group, i.e. five comparisons for each S/PBack to article page