>Treadmill training with body weight support: >Its effect on Parkinson's disease >I Miyai, Y Fujimoto, Y Ueda, H Yamamoto, S Nozaki, T Saito, J Kang >Arch Phys Med Rehabil 2000;81:849-52 > >Ten patients with PD (Hoehn & Yahr stage 2.5-3) were randomized ... >scores improved more with treadmill training than physical therapy (p<0.0005 for each) ... Gimme a break! There is no way that an experiment with only ten subjects can yield statisticaly significant results - and "p<0.0005" suggests an outcome that is overwhelmingly persuasive, not merely significant. Ben Winter