Normalization of temporal-distance parameters in pediatric gait

Abstract

Several techniques for the normalization of temporal-distance parameters in pediatric gait are given. The resulting normalized data can be used to compare (or discriminate) individuals or groups of individuals without the effect of variables such as age and height. The normalization with respect to a reference data set or with respect to the data set itself can be accommodated. Three novel techniques for normalization of gait data have been given: offset, decorrelation and detrending. For normalization of stride length with respect to height, all three are superior to the commonly accepted technique of dividing by the height. The offset technique has obscure units and will have a residual correlation. The decorrelation technique also has obscure units but will have zero correlation provided it is being normalized using a linear model (or piecewise linear model) fitted to the data in a least-squares sense. The detrending technique will also result in a zero correlation if piecewise linear or polynomial models, fitted to the data in a least-squares sense, are used. The detrending technique is the most useful of the three techniques proposed as it will also generate the same units as the original data set and can be easily scaled so that its magnitude is also comparable with the original data. Both the decorrelation and detrending techniques can be used simultaneously to normalize data with respect to two or more variables.