In this paper, we introduce a pivotal goodness of fit test based on empirical kernel density estimation. Our investigation reveals that the new test is more powerful than the traditional goodness of tests found in the literature; namely, the Chi-square and the Kolmogorov-Smirnov (KS) goodness of fit tests. Intensive simulation is conducted to examine the power of the proposed test. Data from a level I Trauma center are used to illustrate the procedures developed in this paper.
Available at: http://works.bepress.com/robert_vogel/180/