THE CONSTRUCTION OF THE SIMPLE X2 AND NEYMAN SMOOTH GOODNESS OF FIT TESTS

Suppose we wish to test whether data are consistent with a completely specified continuous distribution against a general alternative. Familiar omnibus tests are PEARSON'S X² test and NEYMAN'S smooth test. Fundamental problems in the application of these tests are the construction and number of classes to use for X², and the choice of the order of the NEYMAN smooth test. This paper examines these questions.