Parkinson’s disease (PD) is a neurodegenerativedisorder. With progression of PD, movement disorder suchas gait disturbance and balance impairment is frequentlyobserved. Hoehn and Yahr scale (HY) is an indicator to evaluatethe severity of motor signs of PD. Recently, objective measurementcomes to be widely spread. Previous studies pointed outthat human walking comes from complex interaction, and itcomes to be seen as nonlinear dynamics. Amplitude of PDpatients’ stride time variability was reported to be largerthan that of healthy people. Coefficient of variation (CV) iscommonly used to see amplitude of variability. The fractalproperty of PD patients’ stride time is lower than that ofhealthy people. The fractal property was measured by scalingexponent calculated by detrended fluctuation analysis (DFA).However, the relationship between the stride time variabilityand the severity of motor signs of PD remains to be clarified.In this study, we tried to investigate the relationship betweenthese indicators. Clarifying the relationship between practicalseverity index and objective data provides us information tomake a diagnosis of PD. Forty-five PD patients walked 200meter corridor at their preferred pace. As control group, 35healthy people, which include young and elderly people, areparticipated. In order to separate between the PD patientsand healthy people or to classify HY scale, linear discriminantanalysis on both CV and DFA was applied. When we separatedinto all PD patients group and all healthy people group, theaccuracy was 0.76. We tried to separate 2 groups. One is groupof PD patients with HY2.5 or higher and the other is the groupof healthy elderly people or mild PD patients. The specificitywas 0.86. When we tried to separate between PD patients withHY3 and PD patients with HY2.5, the sensitivity was 0.93. Weconclude that gait variability is one of the indicators of motorseverity seen in PD.