Abstract
The class of statistics T, = (Σα i=1, X α i /n)/ x , where α > 0 and ≠ 1, have been considered in the literature for testing exponentiality versus omnibus alternatives. These tests have a twosided rejection region. It is shown here that tests based on these statistics are not consistent for certain alternatives. However, it is shown that one-sided tests based on these statistics are consistent for IFRA (DFRA) distributions. A Monte Carlo power study suggests that lower tail tests based on T ½ and T 2 are very competitive for DFRA and IFRA alternatives, respectively. The null distributions of T ½ and T 2 are approximated by members of the Johnson families of distributions.