Comparison of different goodness-of-fit tests

Various distribution free goodness-of-fit test procedures have been extracted from literature. We present two new binning free tests, the univariate three-region-test and the multivariate energy test. The power of the selected tests with respect to different slowly varying distortions of experimental distributions are investigated. None of the tests is optimum for all distortions. The energy test has high power in many applications and is superior to the chi^2 test.