Huberian statistical approach is applied to neurodegenerative disorder gait rhythm. Gait rhythm dynamics differ between healthy control (CO), Parkinson’s disease (PD), Huntington’s disease (HD) and amyotrophic lateral sclerosis (ALS). Random variables such as stride interval and its two sub-phases (swing and stance) present a great variability with natural outliers (NOs). We propose a different point of view to differentiate diseases and provide new indicators using Huberian statistics approach. A mathematical point of view is developed and experimental results are presented.

Huberian statistics, mixed kernel function, density gap degree, variability gap degree, gait disorder signal, natural outlier, neurodegenerative disease.