The repeatability of gait variables is an important consideration in the clinical use of results of quantitative gait analysis. Statistical measures were used to evaluate repeatability of kinematic, kinetic, and electromyographic data waveforms and spatiotemporal parameters of 40 normal subjects. Subjects were evaluated three times on each test day and on three different test days while walking at their preferred or natural speed. Intrasubject repeatability was excellent for kinematic data in the sagittal plane both within a test day as well as between test days. For joint angle motion in the frontal and transverse planes, the repeatability was good within a test day and poor between test days. Poor between-day repeatability of joint angle motion in the frontal and transverse planes was noted to be partly due to variabilities in the alignment of markers. Vertical reaction and fore-aft shear forces were more repeatable than the mediolateral shear force. Sagittal plane joint moments were more repeatable than frontal or transverse plane moments. For electromyographic data, repeatability within a day was slightly better than between test days. In general, the results demonstrate that with the subjects walking at their natural or preferred speed, the gait variables are quite repeatable. These observations suggest that it may be reasonable to base significant clinical decisions on the results of a single gait evaluation.