Fig. 8: Outlier adjustment procedure for test sittings with two trials. | npj Digital Medicine

Fig. 8: Outlier adjustment procedure for test sittings with two trials.

From: Smartphone-based symbol-digit modalities test reliably captures brain damage in multiple sclerosis

Fig. 8

a Score differences and means for test sittings with two trials are shown on a mixed-effects Bland–Altman plot (HV = 33; MS = 119). The limits of agreement are −11.24 and 10.85, and the mean difference is −0.19. Sittings with differences that fall outside of the limits of agreement, indicated by blue and orange points, are considered to have one trial that is an outlier. b In the sittings with outlier trials, the lower performing trial’s score is increased to reach the limits of agreement thresholds. c The original mixed-effects Bland–Altman plot, now shown with the outlying differences after score adjustment.

Back to article page