Nonparametric testing of first-order structure in point processes on linear networks

In this paper we address a two-sample problem in the context of point processes on linear networks. The aim is to determine whether two given point patterns defined over the same linear network and under the assumption of Poissonness, share the same spatial structure. To do so, a Kolmogorov-Smirnov and a Cram & eacute;r von Mises type test statistics are developed and analysed through an extensive simulation study. We have included different types of networks, balanced and unbalanced sample sizes, and homogeneous and inhomogeneous Poisson point processes. The results show a good level adjustment and high power values, the latter increasing with the sample size and the discrepancy between the two generating intensities. Finally, these methods have also been applied to the analysis of traffic accidents in Rio de Janeiro (Brazil), studying their distribution at different rush hours.