124 – Hypothesis Testing in Nonparametric Problems
Smoothing Goodness-of-Fit Tests Based on Kullback-Leibler Information
Sponsor: Section on Nonparametric Statistics
Keywords: Goodness-of-Fit, Distribution free, Smoothing
Kai-Sheng Song
University of North Texas
Han Yu
Northwest Missouri State University
We present asymptotically distribution-free goodness-of-fit tests based on smoothing techniques. The proposed tests is a nonparametric extension of the classical Neyman-Pearson log-likelihood ratio test. The tests are indicated to have much greater power for detecting high-frequency nonpara- metric alternatives than the existing classical tests such as Kolmogorov-Smirnov tests. This good performance of the proposed tests is demonstrated by Monte Carlo simulations.
