We present a new approach to evaluating the efficiency of some typical statistics for testing the goodness of fit. Since the Pitman approach is too weak to detect sufficiently sharply the differences in efficiency of these statistics, the attention is focused on the Pitman efficiency.
We present a new approach to evaluating the efficiency of some typical statistics for testing the goodness of fit. Since the Pitman approach is too weak to detect sufficiently sharply the differences in efficiency of these statistics, the attention is focused on the Pitman efficiency. (en)