The Asymptotic Sufficiency of a Relatively Small Number of Order Statistics in Tests of Fit
Weiss, Lionel
Ann. Statist., Tome 2 (1974) no. 1, p. 795-802 / Harvested from Project Euclid
For each $n, X_n(1), \cdots, X_n(n)$ are independent and identically distributed continuous random variables over $(0, 1)$, with common density function equal to $1 + r(x)/n^{\frac{1}{2}}, r(x)$ unknown but satisfying certain regularity conditions. The problem is to test the hypothesis that $r(x) = 0$ for all $x$ in (0, 1). $Y_n(1) < \cdots < Y_n(n)$ are the ordered values of $X_n(1), \cdots, X_n(n). \delta$ is a fixed value in the open interval $(\frac{3}{4}, 1)$. It is shown that $Y_n(\lbrack n^\delta\rbrack), Y_n(2\lbrack n^\delta\rbrack), \cdots$ are asymptotically sufficient, and can be assumed to have a joint normal distribution for all asymptotic purposes. Using these facts, a test of the hypothesis is constructed with a good asymptotic power curve.
Publié le : 1974-07-14
Classification:  Tests of fit,  order statistics,  asymptotic efficiency
@article{1176342766,
     author = {Weiss, Lionel},
     title = {The Asymptotic Sufficiency of a Relatively Small Number of Order Statistics in Tests of Fit},
     journal = {Ann. Statist.},
     volume = {2},
     number = {1},
     year = {1974},
     pages = { 795-802},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176342766}
}
Weiss, Lionel. The Asymptotic Sufficiency of a Relatively Small Number of Order Statistics in Tests of Fit. Ann. Statist., Tome 2 (1974) no. 1, pp.  795-802. http://gdmltest.u-ga.fr/item/1176342766/