On the Cramér–von Mises test with parametric hypothesis for poisson processes

Abstract

The problem of the goodness of-fit testing for inhomogeneous Poisson process with parametric basic hypothesis is considered. A test statistic of the Cramer–von Mises type with parameter replaced by the maximum likelihood estimator is proposed and its asymptotic behavior is studied. It is shown that in the case of shift parameter, the limit distribution of the test statistics (under hypothesis) does not depend on the true value of this parameter.