Fig. 1From: A multi-centre, UK-based, non-inferiority randomised controlled trial of 4 follow-up assessment methods in stroke survivorsThe completion rates for postal, online and telephone follow-up methods, compared to face-to-face are shown with the associated 95% confidence intervals. The solid horizontal line is the line of no difference, and the non-inferiority margin (NIM) is shown with the broken horizontal lineBack to article page