作者: Huseyin Gunes , Dennis C. Dietz , Paul F. Auclair , Albert H. Moore
DOI: 10.1016/S0167-9473(96)00056-4
关键词:
摘要: Abstract Modified Kolmogorov-Smirnov (KS), Kuiper (V), Cramer-von Mises (CV), Watson (W), Anderson-Darling (AD) and sequential goodness-of-fit tests are developed for the inverse Gaussian distribution with unknown parameters. A Monte Carlo procedure is employed to generate critical values a wide range of sample sizes shape Power studies indicate that W test most effective against alternate distributions very similar in null distribution. Otherwise, modified AD generally demonstrates highest power among single tests. To eliminate need extensive value tables, functional relationships between values, sizes, parameters reported.