The authors investigate the modified rescaled adjusted range or
statistics as a test for long-range dependence. They show that the modified
statistics has a strong preference for accepting the null hypothesis of no long-range dependence irrespective of whether long-range dependence is present in the data or not. This result implies that when the modified
statistics method indicates that there is no evidence of long-range dependence in a given data set, it is necessary to re-examine the data using a diverse portfolio of time domain-based and frequency domain-based graphical and statistical methods to confirm or to refuse this finding.