作者: Dennis D. Boos
DOI: 10.1080/01621459.1981.10477701
关键词:
摘要: Abstract A weighted Cramer-von Mises distance between the empirical distribution function and assumed model F0(x - θ) is minimized to produce estimators θ n that are asymptotically normal. If weight taken proportional (- ln f 0)″/f 0 , then efficient has appropriate loss of one degree freedom. Special attention focused on limiting this latter goodness-of-fit statistic in both null alternative situations.