Summary
X 1(n),⋯,X n (n) are independent and identically distributed random variables, the common distribution function known to be absolutely continuous, but otherwise unknown. The problem is to test the hypothesis that the unknown cumulative distribution function is some completely specified cumulative distribution functionF(x). LetH n (x) denote the empirical cumulative distribution function based onX 1(n),⋯,X n (n), and let ø(t) denote a given nonnegative bounded weight function defined for 0≦≦1. In [1] the asymptotic distribution of the Cramer-Von Mises statisticW 2 n , defined as
was found, when the hypothesis being tested is true. For the functions ø(t) considered in [1], this asymptotic distribution is not normal. In this paper it is shown that under alternative cumulative distribution functions not too close toF(x),W 2 n is asymptotically normally distributed.
Similar content being viewed by others
References
T. W. Anderson and D. A. Darling,“Asymptotic theory of certain ‘goodness of fit’ criteria based on stochastic processes,” Ann. Math. Statist., 23 (1952), 193–212.
Wassily Hoeffding, “ Asymptotically optimal tests for multinomial distributions,” Ann. Math. Statist., 36 (1965), 369–401.
Author information
Authors and Affiliations
Additional information
Research supported by National Science Foundation Grant No. GP 3783.
About this article
Cite this article
Weiss, L. On the asymptotic power of cramér-von mises tests of fit. Ann Inst Stat Math 18, 149–153 (1966). https://doi.org/10.1007/BF02869526
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02869526