A law of the iterated logarithm for the heavily trimmed sums
被引:0
|
作者:
Wang, F.
论文数: 0引用数: 0
h-index: 0
机构:
Dept. of Probability and Statistics, School of Mathematical Sciences, Peking University, Beijing, 100871, ChinaDept. of Probability and Statistics, School of Mathematical Sciences, Peking University, Beijing, 100871, China
Wang, F.
[1
]
Cheng, S.
论文数: 0引用数: 0
h-index: 0
机构:
Dept. of Probability and Statistics, School of Mathematical Sciences, Peking University, Beijing, 100871, ChinaDept. of Probability and Statistics, School of Mathematical Sciences, Peking University, Beijing, 100871, China
Cheng, S.
[1
]
机构:
[1] Dept. of Probability and Statistics, School of Mathematical Sciences, Peking University, Beijing, 100871, China
Let {Xn, n greater than or equal 1} be a sequence of i.i.d. random variables with common d.f. F(x). X1,n [less-than or equal to] ... [less-than or equal to] Xn,n are its order statistics. Q is the quantile function of F. It is shown that for any underlying distribution function F, the LIL for the heavily trimmed sums remains true, as long as λ and 1 - λ are continuity points of Q and σ(λ) > 0. Moreover, a strong approximation result is obtained in this case.