An empirical comparison of block and round norms for modelling actual distances

Distance predicting functions may be used in a variety of applications. This article examines the accuracy of two distance-predicting-function families, the norm and the block norms, by conducting an empirical study. The empirical study uses actual travel distance from seventeen geographical regions. The normality of the random variables which are used to construct statistical tests to compare the accuracy of the norms is examined by using Q-Q plots and sample Pearson coefficients. The results indicate that the norm is more accurate than the three parameter block norm and within the block norm family, the accuracy of a norm increased as the number of parameters of the norm increased.